CWE-770
AllowedAllocation of Resources Without Limits or Throttling
Abstraction: Base · Status: Incomplete
The product allocates a reusable resource or group of resources on behalf of an actor without imposing any intended restrictions on the size or number of resources that can be allocated.
3745 vulnerabilities reference this CWE, most recent first.
GHSA-8PF8-F3WP-VF64
Vulnerability from github – Published: 2024-06-28 18:31 – Updated: 2024-06-28 18:31IBM MQ 9.0 LTS, 9.1 LTS, 9.2 LTS, 9.3 LTS and 9.3 CD, in certain configurations, is vulnerable to a denial of service attack caused by an error processing messages when an API Exit using MQBUFMH is used. IBM X-Force ID: 290259.
{
"affected": [],
"aliases": [
"CVE-2024-31919"
],
"database_specific": {
"cwe_ids": [
"CWE-770"
],
"github_reviewed": false,
"github_reviewed_at": null,
"nvd_published_at": "2024-06-28T18:15:03Z",
"severity": "MODERATE"
},
"details": "IBM MQ 9.0 LTS, 9.1 LTS, 9.2 LTS, 9.3 LTS and 9.3 CD, in certain configurations, is vulnerable to a denial of service attack caused by an error processing messages when an API Exit using MQBUFMH is used. IBM X-Force ID: 290259.",
"id": "GHSA-8pf8-f3wp-vf64",
"modified": "2024-06-28T18:31:42Z",
"published": "2024-06-28T18:31:42Z",
"references": [
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2024-31919"
},
{
"type": "WEB",
"url": "https://exchange.xforce.ibmcloud.com/vulnerabilities/290259"
},
{
"type": "WEB",
"url": "https://www.ibm.com/support/pages/node/7157979"
}
],
"schema_version": "1.4.0",
"severity": [
{
"score": "CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H",
"type": "CVSS_V3"
}
]
}
GHSA-8PGV-569H-W5RW
Vulnerability from github – Published: 2023-11-12 15:55 – Updated: 2025-10-28 18:22Summary
The grpc Unary Server Interceptor opentelemetry-go-contrib/instrumentation/google.golang.org/grpc/otelgrpc/interceptor.go
// UnaryServerInterceptor returns a grpc.UnaryServerInterceptor suitable
// for use in a grpc.NewServer call.
func UnaryServerInterceptor(opts ...Option) grpc.UnaryServerInterceptor {
out of the box adds labels
net.peer.sock.addrnet.peer.sock.port
that have unbound cardinality. It leads to the server's potential memory exhaustion when many malicious requests are sent.
Details
An attacker can easily flood the peer address and port for requests.
PoC
Apply the attached patch to the example and run the client multiple times. Observe how each request will create a unique histogram and how the memory consumption increases during it.
Impact
In order to be affected, the program has to configure a metrics pipeline, use UnaryServerInterceptor, and does not filter any client IP address and ports via middleware or proxies, etc.
Others
It is similar to already reported vulnerabilities.
- GHSA-rcjv-mgp8-qvmr (open-telemetry/opentelemetry-go-contrib)
- GHSA-5r5m-65gx-7vrh (open-telemetry/opentelemetry-go-contrib)
- GHSA-cg3q-j54f-5p7p (prometheus/client_golang)
Workaround for affected versions
As a workaround to stop being affected, a view removing the attributes can be used.
The other possibility is to disable grpc metrics instrumentation by passing otelgrpc.WithMeterProvider option with noop.NewMeterProvider.
Solution provided by upgrading
In PR #4322, to be released with v0.46.0, the attributes were removed.
References
{
"affected": [
{
"package": {
"ecosystem": "Go",
"name": "go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc"
},
"ranges": [
{
"events": [
{
"introduced": "0.37.0"
},
{
"fixed": "0.46.0"
}
],
"type": "ECOSYSTEM"
}
]
}
],
"aliases": [
"CVE-2023-47108"
],
"database_specific": {
"cwe_ids": [
"CWE-770"
],
"github_reviewed": true,
"github_reviewed_at": "2023-11-12T15:55:39Z",
"nvd_published_at": "2023-11-10T19:15:16Z",
"severity": "HIGH"
},
"details": "### Summary\n\nThe grpc Unary Server Interceptor [opentelemetry-go-contrib/instrumentation/google.golang.org/grpc/otelgrpc/interceptor.go](https://github.com/open-telemetry/opentelemetry-go-contrib/blob/9d4eb7e7706038b07d33f83f76afbe13f53d171d/instrumentation/google.golang.org/grpc/otelgrpc/interceptor.go#L327)\n\n```\n// UnaryServerInterceptor returns a grpc.UnaryServerInterceptor suitable\n// for use in a grpc.NewServer call.\nfunc UnaryServerInterceptor(opts ...Option) grpc.UnaryServerInterceptor {\n```\n \nout of the box adds labels\n\n- `net.peer.sock.addr`\n- `net.peer.sock.port`\n\nthat have unbound cardinality. It leads to the server\u0027s potential memory exhaustion when many malicious requests are sent.\n\n### Details\n\nAn attacker can easily flood the peer address and port for requests. \n\n### PoC\n\nApply the attached patch to the example and run the client multiple times. Observe how each request will create a unique histogram and how the memory consumption increases during it.\n### Impact\n\nIn order to be affected, the program has to configure a metrics pipeline, use [UnaryServerInterceptor](https://github.com/open-telemetry/opentelemetry-go-contrib/blob/9d4eb7e7706038b07d33f83f76afbe13f53d171d/instrumentation/google.golang.org/grpc/otelgrpc/interceptor.go#L327), and does not filter any client IP address and ports via middleware or proxies, etc.\n\n### Others\n\nIt is similar to already reported vulnerabilities.\n\n* [GHSA-rcjv-mgp8-qvmr](https://github.com/open-telemetry/opentelemetry-go-contrib/security/advisories/GHSA-rcjv-mgp8-qvmr) ([open-telemetry/opentelemetry-go-contrib](https://github.com/open-telemetry/opentelemetry-go-contrib))\n- [GHSA-5r5m-65gx-7vrh](https://github.com/open-telemetry/opentelemetry-go-contrib/security/advisories/GHSA-5r5m-65gx-7vrh \"GHSA-5r5m-65gx-7vrh\") ([open-telemetry/opentelemetry-go-contrib](https://github.com/open-telemetry/opentelemetry-go-contrib))\n- [GHSA-cg3q-j54f-5p7p](https://github.com/advisories/GHSA-cg3q-j54f-5p7p \"GHSA-cg3q-j54f-5p7p\") ([prometheus/client_golang](https://github.com/prometheus/client_golang))\n\n### Workaround for affected versions\n\nAs a workaround to stop being affected, a view removing the attributes can be used.\n\nThe other possibility is to disable grpc metrics instrumentation by passing [`otelgrpc.WithMeterProvider`](https://github.com/open-telemetry/opentelemetry-go-contrib/blob/instrumentation/google.golang.org/grpc/otelgrpc/v0.45.0/instrumentation/google.golang.org/grpc/otelgrpc/config.go#L138) option with [`noop.NewMeterProvider`](https://pkg.go.dev/go.opentelemetry.io/otel/metric/noop#NewMeterProvider).\n\n### Solution provided by upgrading\n\nIn PR [#4322](https://github.com/open-telemetry/opentelemetry-go-contrib/pull/4322), to be released with v0.46.0, the attributes were removed.\n\n### References\n\n- [#4322](https://github.com/open-telemetry/opentelemetry-go-contrib/pull/4322)",
"id": "GHSA-8pgv-569h-w5rw",
"modified": "2025-10-28T18:22:23Z",
"published": "2023-11-12T15:55:39Z",
"references": [
{
"type": "WEB",
"url": "https://github.com/open-telemetry/opentelemetry-go-contrib/security/advisories/GHSA-8pgv-569h-w5rw"
},
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2023-47108"
},
{
"type": "WEB",
"url": "https://github.com/open-telemetry/opentelemetry-go-contrib/pull/4322"
},
{
"type": "WEB",
"url": "https://github.com/open-telemetry/opentelemetry-go-contrib/commit/04c5dcbb5b35f14b4e6793b245919c72addbc7d0"
},
{
"type": "WEB",
"url": "https://github.com/open-telemetry/opentelemetry-go-contrib/commit/b44dfc9092b157625a5815cb437583cee663333b"
},
{
"type": "PACKAGE",
"url": "https://github.com/open-telemetry/opentelemetry-go-contrib"
},
{
"type": "WEB",
"url": "https://github.com/open-telemetry/opentelemetry-go-contrib/blob/9d4eb7e7706038b07d33f83f76afbe13f53d171d/instrumentation/google.golang.org/grpc/otelgrpc/interceptor.go#L327"
},
{
"type": "WEB",
"url": "https://github.com/open-telemetry/opentelemetry-go-contrib/blob/instrumentation/google.golang.org/grpc/otelgrpc/v0.45.0/instrumentation/google.golang.org/grpc/otelgrpc/config.go#L138"
},
{
"type": "WEB",
"url": "https://pkg.go.dev/go.opentelemetry.io/otel/metric/noop#NewMeterProvider"
}
],
"schema_version": "1.4.0",
"severity": [
{
"score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H",
"type": "CVSS_V3"
}
],
"summary": "otelgrpc DoS vulnerability due to unbound cardinality metrics "
}
GHSA-8PM6-575P-R3MV
Vulnerability from github – Published: 2024-10-11 18:32 – Updated: 2024-10-11 18:32An Allocation of Resources Without Limits or Throttling vulnerability in the kernel of Juniper Networks Junos OS Evolved allows an unauthenticated, network based attacker to cause a Denial of Service (DoS).
In specific cases the state of TCP sessions that are terminated is not cleared, which over time leads to an exhaustion of resources, preventing new connections to the control plane from being established.
A continuously increasing number of connections shown by:
user@host > show system connections
is indicative of the problem. To recover the respective RE needs to be restarted manually.
This issue only affects IPv4 but does not affect IPv6. This issue only affects TCP sessions established in-band (over an interface on an FPC) but not out-of-band (over the management ethernet port on the routing-engine).
This issue affects Junos OS Evolved:
- All versions before 21.4R3-S9-EVO,
- 22.2 versions before 22.2R3-S4-EVO,
- 22.4 version before 22.4R3-S3-EVO,
- 23.2 versions before 23.2R2-S1-EVO,
- 23.4 versions before 23.4R2-EVO.
{
"affected": [],
"aliases": [
"CVE-2024-47502"
],
"database_specific": {
"cwe_ids": [
"CWE-770"
],
"github_reviewed": false,
"github_reviewed_at": null,
"nvd_published_at": "2024-10-11T16:15:11Z",
"severity": "HIGH"
},
"details": "An Allocation of Resources Without Limits or Throttling vulnerability in the kernel of Juniper Networks Junos OS Evolved allows an unauthenticated, network based attacker to cause a Denial of Service (DoS).\n\nIn specific cases the state of TCP sessions that are terminated is not cleared, which over time leads to an exhaustion of resources, preventing new connections to the control plane from being established.\n\nA continuously increasing number of connections shown by:\n\n\n\nuser@host \u003e show system connections\n\n\n\nis indicative of the problem. To recover the respective RE needs to be restarted manually.\n\nThis issue only affects IPv4 but does not affect IPv6.\nThis issue only affects TCP sessions established in-band (over an interface on an FPC) but not out-of-band (over the management ethernet port on the routing-engine).\n\nThis issue affects Junos OS Evolved:\u00a0\n\n * All versions before 21.4R3-S9-EVO,\n * 22.2 versions before 22.2R3-S4-EVO,\n * 22.4 version before 22.4R3-S3-EVO,\n * 23.2 versions before 23.2R2-S1-EVO,\n * 23.4 versions before 23.4R2-EVO.",
"id": "GHSA-8pm6-575p-r3mv",
"modified": "2024-10-11T18:32:49Z",
"published": "2024-10-11T18:32:49Z",
"references": [
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2024-47502"
},
{
"type": "WEB",
"url": "https://supportportal.juniper.net/JSA88132"
}
],
"schema_version": "1.4.0",
"severity": [
{
"score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H",
"type": "CVSS_V3"
},
{
"score": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:L/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:Y/R:U/V:X/RE:M/U:X",
"type": "CVSS_V4"
}
]
}
GHSA-8PMR-CC7F-4V7W
Vulnerability from github – Published: 2026-07-08 03:30 – Updated: 2026-07-08 03:30sshd in OpenSSH before 10.4 does not always honor the minimum authentication delay.
{
"affected": [],
"aliases": [
"CVE-2026-60001"
],
"database_specific": {
"cwe_ids": [
"CWE-770"
],
"github_reviewed": false,
"github_reviewed_at": null,
"nvd_published_at": "2026-07-08T01:16:29Z",
"severity": "MODERATE"
},
"details": "sshd in OpenSSH before 10.4 does not always honor the minimum authentication delay.",
"id": "GHSA-8pmr-cc7f-4v7w",
"modified": "2026-07-08T03:30:27Z",
"published": "2026-07-08T03:30:27Z",
"references": [
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2026-60001"
},
{
"type": "WEB",
"url": "https://marc.info/?l=openssh-unix-dev\u0026m=178333966933090\u0026w=2"
},
{
"type": "WEB",
"url": "https://www.openssh.org/releasenotes.html#10.4p1"
},
{
"type": "WEB",
"url": "https://www.openwall.com/lists/oss-security/2026/07/06/5"
}
],
"schema_version": "1.4.0",
"severity": [
{
"score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:L",
"type": "CVSS_V3"
}
]
}
GHSA-8PPH-7GJG-6JJP
Vulnerability from github – Published: 2025-04-11 04:19 – Updated: 2025-04-11 04:19IBM QRadar WinCollect Agent 10.0 through 10.1.13 could allow a remote attacker to cause a denial of service by interrupting an HTTP request that could consume memory resources.
{
"affected": [],
"aliases": [
"CVE-2024-51461"
],
"database_specific": {
"cwe_ids": [
"CWE-770"
],
"github_reviewed": false,
"github_reviewed_at": null,
"nvd_published_at": "2025-04-11T02:15:17Z",
"severity": "MODERATE"
},
"details": "IBM QRadar WinCollect Agent 10.0 through 10.1.13 could allow a remote attacker to cause a denial of service by interrupting an HTTP request that could consume memory resources.",
"id": "GHSA-8pph-7gjg-6jjp",
"modified": "2025-04-11T04:19:26Z",
"published": "2025-04-11T04:19:26Z",
"references": [
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2024-51461"
},
{
"type": "WEB",
"url": "https://www.ibm.com/support/pages/node/7230614"
}
],
"schema_version": "1.4.0",
"severity": [
{
"score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:L",
"type": "CVSS_V3"
}
]
}
GHSA-8PW2-6JV3-MJ5J
Vulnerability from github – Published: 2026-09-17 17:17 – Updated: 2026-09-17 17:17Summary
Current vLLM main lets an inference request choose the PyNvVideoCodec GPU video decoder through media_io_kwargs.video.video_backend, but engine GPU memory reservation is computed only from static startup configuration and VLLM_VIDEO_LOADER_BACKEND. If the server starts with the default OpenCV/software backend and no --mm-ipc-gpu-memory-gb budget, a client can still route a video request into the PyNvVideoCodec path after startup, causing frontend CUDA-context, decoder-surface, and decoded-frame GPU allocations that were not carved out of the engine KV-cache budget.
Technical Details
The vulnerable boundary is the split between request-time media decoding choices in the API server and startup-time memory budgeting in the engine worker. Request bodies for Chat Completions and Responses expose media_io_kwargs, and those values are forwarded to the shared media connector. For video inputs, MediaConnector.fetch_video() copies self.media_io_kwargs["video"] into video_io_kwargs, only setting a model-derived backend when video_backend is absent. VideoMediaIO.__init__() then consumes video_backend from those kwargs and loads that backend from VIDEO_LOADER_REGISTRY.
The relevant request-side source path is:
video_io_kwargs = dict(self.media_io_kwargs.get("video", {}))
if "video_backend" not in video_io_kwargs and (
video_backend := get_video_loader_backend_for_processor(video_processor)
):
video_io_kwargs["video_backend"] = video_backend
video_io = VideoMediaIO(image_io, **video_io_kwargs)
video_loader_backend = (
kwargs.pop("video_backend", None) or envs.VLLM_VIDEO_LOADER_BACKEND
)
self.video_loader = VIDEO_LOADER_REGISTRY.load(video_loader_backend)
VideoBackend.load_bytes() then dispatches backend == "pynvvideocodec" into decode_frames_pynvvideocodec(), which constructs a PyNvVideoCodec decoder, creates or uses a CUDA stream, reads stream metadata, decodes selected frames on the GPU, and copies those frames into pinned host memory. The new frontend GPU memory pool accounts only for raw decoded frame bytes when a pool exists; it does not make request-time backend selection safe when no startup reservation was made.
The engine-side reservation code makes its decision from static model config and environment only:
def _uses_pynvvideocodec_video_backend(mm_config) -> bool:
video_kwargs = mm_config.media_io_kwargs.get("video", {})
video_loader_backend = (
video_kwargs.get("video_backend") or envs.VLLM_VIDEO_LOADER_BACKEND
)
codec_backend = video_kwargs.get("backend")
return (
video_loader_backend == PYNVVIDEOCODEC_VIDEO_BACKEND
or codec_backend == PYNVVIDEOCODEC_VIDEO_BACKEND
)
decoder_reserved_bytes = (
num_api_servers * per_server_decoder_bytes
if self._uses_pynvvideocodec_video_backend(mm_config)
else 0
)
reserved_bytes = raw_frame_reserved_bytes + decoder_reserved_bytes
if reserved_bytes <= 0:
return available_kv_cache_memory_bytes
With default static video configuration, mm_config.media_io_kwargs["video"] does not name PyNvVideoCodec and VLLM_VIDEO_LOADER_BACKEND defaults to OpenCV/software decoding. The worker therefore reserves no PyNv decoder/CUDA-context bytes. A later request can still set media_io_kwargs.video.video_backend="pynvvideocodec" and reach the GPU decoder path because that runtime field is intentionally honored by VideoMediaIO.
PoV
An ordinary multimodal inference request can carry the backend override in the request body:
{
"model": "served-vlm",
"messages": [
{
"role": "user",
"content": [
{"type": "text", "text": "summarize this clip"},
{"type": "video_url", "video_url": {"url": "data:video/mp4;base64,<small-mp4>"}}
]
}
],
"media_io_kwargs": {
"video": {
"video_backend": "pynvvideocodec"
}
}
}
The following bounded source-level check confirms the code path without allocating GPU memory:
git clone --filter=blob:none https://github.com/vllm-project/vllm.git
cd vllm
git checkout ddd3855a28a561a5bb54d380c6e6b8b1e883cc4a
python3 check_pynv_backend_reservation.py --repo .
PoC
The bounded check validates current source markers, simulates the exact static reservation predicate, and compares vulnerable and negative-control configurations. Key output:
{
"vulnerable": true,
"head": "ddd3855a28a561a5bb54d380c6e6b8b1e883cc4a",
"reservation_simulation": {
"env_video_loader_backend": "opencv",
"request_selects_pynv_after_startup": true,
"vulnerable_static_reserved_bytes": 0,
"negative_control_static_pynv_reserved_bytes": 2066953011,
"raw_frame_only_control_reserved_bytes": 268435456,
"unreserved_decoder_bytes_when_only_request_selects_pynv": 2066953011
}
}
The negative control is important: when PyNvVideoCodec is selected statically, the worker reserves 2066953011 bytes per API process for decoder surfaces plus CUDA context. The vulnerable case reserves 0 bytes for the same decoder overhead because PyNvVideoCodec is selected only by the later request. A second control with static OpenCV plus mm_ipc_gpu_memory_gb=0.25 reserves only the raw-frame semaphore budget and still does not reserve PyNv decoder/CUDA-context bytes.
Impact
An attacker who can submit video requests to a vLLM deployment with PyNvVideoCodec available can force frontend GPU decoding even when the engine did not reserve memory for that decoder during startup. On high-utilization serving deployments, the unreserved CUDA context, retained decoder surfaces, and decoded-frame allocations can reduce or exhaust GPU memory that the engine assumed was available for weights, activations, or KV cache, causing request failures, worker crashes, or service-level denial of service.
Suggested severity is Medium with conservative CVSS v3.1 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H (6.5). If a deployment exposes the affected API without authentication, PR:N would raise the deployment-specific score. Suggested weaknesses are CWE-770 (Allocation of Resources Without Limits or Throttling) and CWE-400 (Uncontrolled Resource Consumption). This should not be rated Low because the affected resource is shared GPU memory in the serving path and the code already treats the PyNv decoder/CUDA-context footprint as large enough to reserve at startup when statically configured.
Limitations: exploitation requires a GPU deployment where PyNvVideoCodec is installed and usable, and the request must reach a video-capable model/path. The issue does not claim code execution, data disclosure, or SSRF.
Suggested Fix
Do not allow untrusted request fields to select a GPU decoder that was not included in startup memory reservation. The simplest fix is to reject request-level media_io_kwargs.video.video_backend="pynvvideocodec" unless the static server configuration already selected PyNvVideoCodec and reserved its decoder/CUDA-context budget.
If dynamic backend selection remains supported, split software and GPU decoder policies: allow request selection among CPU/software decoders only, require an explicit operator allowlist for GPU decoders, and include every request-selectable GPU decoder in the startup reservation predicate. Add regression coverage for static OpenCV startup config plus request-level PyNvVideoCodec override, and preserve the negative control where static PyNvVideoCodec configuration reserves decoder/CUDA-context bytes.
Affected Package/Versions
Package: vllm from vllm-project/vllm.
Confirmed affected: current main at ddd3855a28a561a5bb54d380c6e6b8b1e883cc4a.
Introduced by: af16446bf39de047ab57649c933063cf1cbf1e50, Vram semaphore infra (#44465), committed 2026-06-26T17:32:51-07:00.
Release status checked: git tag --contains af16446bf returned no release tags in the fresh checkout. GitHub repository metadata reported latest published release v0.23.0 published 2026-06-15T05:27:20Z; the local v0.24.0 tag also does not contain the introducing commit. The affected range should therefore be current main builds containing af16446bf until fixed, rather than a confirmed released-version range.
Advisory History
Public vLLM advisories checked included audio decompression-bomb DoS, unbounded video/jpeg frame-count DoS, MediaConnector SSRF, video processing RCE, multimodal embedding DoS/RCE, GGUF GPU memory exposure, multimodal hashing, and other request-parameter DoS classes. None matched request-selected PyNvVideoCodec or the static VRAM reservation mismatch.
Prior local/private vLLM report families checked included request-level media_io_kwargs reopening video/jpeg frame fanout, GLM video metadata amplification, and audio media decode duration-limit bypass. Those reports share the request-level media kwargs boundary, but they target CPU/media decode limits or model metadata amplification. This report targets a different privileged asset and fix surface: GPU decoder selection after engine startup memory reservation.
Focused GitHub issue/PR searches for pynvvideocodec, mm_ipc_gpu_memory, video_backend media_io_kwargs, Vram semaphore infra, and frontend multimodal GPU decoding found the PyNvVideoCodec zero-copy RFC, an old do-not-review prototype, merged PR #44465, and an unrelated TorchCodec backend PR. No public issue or PR described this security boundary.
Appendix: Bounded Source-Level Check
#!/usr/bin/env python3
from __future__ import annotations
import argparse
import json
import re
import subprocess
from pathlib import Path
MIB = 1024 * 1024
GIB = 1024 * MIB
def read(repo: Path, rel: str) -> str:
return (repo / rel).read_text(encoding="utf-8")
def const_int(source: str, name: str) -> int:
expr = re.search(rf"^{name}\s*=\s*(.+)$", source, flags=re.MULTILINE).group(1).strip()
if expr == "128 * MiB_bytes":
return 128 * MIB
if expr == "int(1.8 * 1024 * MiB_bytes)":
return int(1.8 * 1024 * MIB)
if expr == "1":
return 1
raise AssertionError(expr)
def uses_pynv_static(static_media_io_kwargs: dict[str, dict[str, str]], env_backend: str) -> bool:
video_kwargs = static_media_io_kwargs.get("video", {})
video_loader_backend = video_kwargs.get("video_backend") or env_backend
codec_backend = video_kwargs.get("backend")
return video_loader_backend == "pynvvideocodec" or codec_backend == "pynvvideocodec"
def reserve_bytes(static_media_io_kwargs, env_backend, mm_ipc_gpu_memory_gb, decoder_bytes, cuda_context_bytes, retained_decoders):
raw_frame_reserved_bytes = int(mm_ipc_gpu_memory_gb * GIB)
per_server_decoder_bytes = decoder_bytes * retained_decoders + cuda_context_bytes
decoder_reserved_bytes = per_server_decoder_bytes if uses_pynv_static(static_media_io_kwargs, env_backend) else 0
return raw_frame_reserved_bytes + decoder_reserved_bytes
parser = argparse.ArgumentParser()
parser.add_argument("--repo", required=True, type=Path)
repo = parser.parse_args().repo.resolve()
media_video = read(repo, "vllm/multimodal/media/video.py")
connector = read(repo, "vllm/multimodal/media/connector.py")
chat_protocol = read(repo, "vllm/entrypoints/openai/chat_completion/protocol.py")
responses_protocol = read(repo, "vllm/entrypoints/openai/responses/protocol.py")
gpu_worker = read(repo, "vllm/v1/worker/gpu_worker.py")
video_core = read(repo, "vllm/multimodal/video.py")
assert "media_io_kwargs: dict[str, dict[str, Any]] | None = Field(" in chat_protocol
assert "media_io_kwargs: dict[str, dict[str, Any]] | None = Field(" in responses_protocol
assert 'video_io_kwargs = dict(self.media_io_kwargs.get("video", {}))' in connector
assert 'if "video_backend" not in video_io_kwargs and (' in connector
assert 'kwargs.pop("video_backend", None) or envs.VLLM_VIDEO_LOADER_BACKEND' in media_video
assert "elif backend == PYNVVIDEOCODEC_VIDEO_BACKEND:" in video_core
assert 'video_kwargs = mm_config.media_io_kwargs.get("video", {})' in gpu_worker
decoder_bytes = const_int(video_core, "PYNVVIDEOCODEC_DECODER_GPU_MEMORY_BYTES")
retained_decoders = const_int(video_core, "PYNVVIDEOCODEC_MAX_RETAINED_DECODERS")
cuda_context_bytes = const_int(video_core, "PYNVVIDEOCODEC_CUDA_CONTEXT_BYTES")
per_server_decoder_bytes = decoder_bytes * retained_decoders + cuda_context_bytes
vulnerable_static_reserved = reserve_bytes({}, "opencv", 0.0, decoder_bytes, cuda_context_bytes, retained_decoders)
negative_control_reserved = reserve_bytes({"video": {"video_backend": "pynvvideocodec"}}, "opencv", 0.0, decoder_bytes, cuda_context_bytes, retained_decoders)
raw_frame_only_control = reserve_bytes({}, "opencv", 0.25, decoder_bytes, cuda_context_bytes, retained_decoders)
head = subprocess.check_output(["git", "-C", str(repo), "rev-parse", "HEAD"], text=True).strip()
print(json.dumps({
"head": head,
"vulnerable": vulnerable_static_reserved == 0 and negative_control_reserved == per_server_decoder_bytes,
"reservation_simulation": {
"env_video_loader_backend": "opencv",
"request_selects_pynv_after_startup": True,
"vulnerable_static_reserved_bytes": vulnerable_static_reserved,
"negative_control_static_pynv_reserved_bytes": negative_control_reserved,
"raw_frame_only_control_reserved_bytes": raw_frame_only_control,
"unreserved_decoder_bytes_when_only_request_selects_pynv": per_server_decoder_bytes,
},
}, indent=2, sort_keys=True))
{
"affected": [
{
"package": {
"ecosystem": "PyPI",
"name": "vllm"
},
"ranges": [
{
"events": [
{
"introduced": "0"
},
{
"fixed": "0.28.0"
}
],
"type": "ECOSYSTEM"
}
]
}
],
"aliases": [
"CVE-2026-69147"
],
"database_specific": {
"cwe_ids": [
"CWE-400",
"CWE-770"
],
"github_reviewed": true,
"github_reviewed_at": "2026-09-17T17:17:39Z",
"nvd_published_at": "2026-09-16T18:17:11Z",
"severity": "MODERATE"
},
"details": "## Summary\n\nCurrent vLLM `main` lets an inference request choose the PyNvVideoCodec GPU video decoder through `media_io_kwargs.video.video_backend`, but engine GPU memory reservation is computed only from static startup configuration and `VLLM_VIDEO_LOADER_BACKEND`. If the server starts with the default OpenCV/software backend and no `--mm-ipc-gpu-memory-gb` budget, a client can still route a video request into the PyNvVideoCodec path after startup, causing frontend CUDA-context, decoder-surface, and decoded-frame GPU allocations that were not carved out of the engine KV-cache budget.\n\n## Technical Details\n\nThe vulnerable boundary is the split between request-time media decoding choices in the API server and startup-time memory budgeting in the engine worker. Request bodies for Chat Completions and Responses expose `media_io_kwargs`, and those values are forwarded to the shared media connector. For video inputs, `MediaConnector.fetch_video()` copies `self.media_io_kwargs[\"video\"]` into `video_io_kwargs`, only setting a model-derived backend when `video_backend` is absent. `VideoMediaIO.__init__()` then consumes `video_backend` from those kwargs and loads that backend from `VIDEO_LOADER_REGISTRY`.\n\nThe relevant request-side source path is:\n\n```python\nvideo_io_kwargs = dict(self.media_io_kwargs.get(\"video\", {}))\nif \"video_backend\" not in video_io_kwargs and (\n video_backend := get_video_loader_backend_for_processor(video_processor)\n):\n video_io_kwargs[\"video_backend\"] = video_backend\nvideo_io = VideoMediaIO(image_io, **video_io_kwargs)\n```\n\n```python\nvideo_loader_backend = (\n kwargs.pop(\"video_backend\", None) or envs.VLLM_VIDEO_LOADER_BACKEND\n)\nself.video_loader = VIDEO_LOADER_REGISTRY.load(video_loader_backend)\n```\n\n`VideoBackend.load_bytes()` then dispatches `backend == \"pynvvideocodec\"` into `decode_frames_pynvvideocodec()`, which constructs a PyNvVideoCodec decoder, creates or uses a CUDA stream, reads stream metadata, decodes selected frames on the GPU, and copies those frames into pinned host memory. The new frontend GPU memory pool accounts only for raw decoded frame bytes when a pool exists; it does not make request-time backend selection safe when no startup reservation was made.\n\nThe engine-side reservation code makes its decision from static model config and environment only:\n\n```python\ndef _uses_pynvvideocodec_video_backend(mm_config) -\u003e bool:\n video_kwargs = mm_config.media_io_kwargs.get(\"video\", {})\n video_loader_backend = (\n video_kwargs.get(\"video_backend\") or envs.VLLM_VIDEO_LOADER_BACKEND\n )\n codec_backend = video_kwargs.get(\"backend\")\n return (\n video_loader_backend == PYNVVIDEOCODEC_VIDEO_BACKEND\n or codec_backend == PYNVVIDEOCODEC_VIDEO_BACKEND\n )\n```\n\n```python\ndecoder_reserved_bytes = (\n num_api_servers * per_server_decoder_bytes\n if self._uses_pynvvideocodec_video_backend(mm_config)\n else 0\n)\nreserved_bytes = raw_frame_reserved_bytes + decoder_reserved_bytes\nif reserved_bytes \u003c= 0:\n return available_kv_cache_memory_bytes\n```\n\nWith default static video configuration, `mm_config.media_io_kwargs[\"video\"]` does not name PyNvVideoCodec and `VLLM_VIDEO_LOADER_BACKEND` defaults to OpenCV/software decoding. The worker therefore reserves no PyNv decoder/CUDA-context bytes. A later request can still set `media_io_kwargs.video.video_backend=\"pynvvideocodec\"` and reach the GPU decoder path because that runtime field is intentionally honored by `VideoMediaIO`.\n\n## PoV\n\nAn ordinary multimodal inference request can carry the backend override in the request body:\n\n```json\n{\n \"model\": \"served-vlm\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": [\n {\"type\": \"text\", \"text\": \"summarize this clip\"},\n {\"type\": \"video_url\", \"video_url\": {\"url\": \"data:video/mp4;base64,\u003csmall-mp4\u003e\"}}\n ]\n }\n ],\n \"media_io_kwargs\": {\n \"video\": {\n \"video_backend\": \"pynvvideocodec\"\n }\n }\n}\n```\n\nThe following bounded source-level check confirms the code path without allocating GPU memory:\n\n```bash\ngit clone --filter=blob:none https://github.com/vllm-project/vllm.git\ncd vllm\ngit checkout ddd3855a28a561a5bb54d380c6e6b8b1e883cc4a\npython3 check_pynv_backend_reservation.py --repo .\n```\n\n## PoC\n\nThe bounded check validates current source markers, simulates the exact static reservation predicate, and compares vulnerable and negative-control configurations. Key output:\n\n```json\n{\n \"vulnerable\": true,\n \"head\": \"ddd3855a28a561a5bb54d380c6e6b8b1e883cc4a\",\n \"reservation_simulation\": {\n \"env_video_loader_backend\": \"opencv\",\n \"request_selects_pynv_after_startup\": true,\n \"vulnerable_static_reserved_bytes\": 0,\n \"negative_control_static_pynv_reserved_bytes\": 2066953011,\n \"raw_frame_only_control_reserved_bytes\": 268435456,\n \"unreserved_decoder_bytes_when_only_request_selects_pynv\": 2066953011\n }\n}\n```\n\nThe negative control is important: when PyNvVideoCodec is selected statically, the worker reserves `2066953011` bytes per API process for decoder surfaces plus CUDA context. The vulnerable case reserves `0` bytes for the same decoder overhead because PyNvVideoCodec is selected only by the later request. A second control with static OpenCV plus `mm_ipc_gpu_memory_gb=0.25` reserves only the raw-frame semaphore budget and still does not reserve PyNv decoder/CUDA-context bytes.\n\n## Impact\n\nAn attacker who can submit video requests to a vLLM deployment with PyNvVideoCodec available can force frontend GPU decoding even when the engine did not reserve memory for that decoder during startup. On high-utilization serving deployments, the unreserved CUDA context, retained decoder surfaces, and decoded-frame allocations can reduce or exhaust GPU memory that the engine assumed was available for weights, activations, or KV cache, causing request failures, worker crashes, or service-level denial of service.\n\nSuggested severity is Medium with conservative CVSS v3.1 `CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H` (6.5). If a deployment exposes the affected API without authentication, `PR:N` would raise the deployment-specific score. Suggested weaknesses are `CWE-770` (Allocation of Resources Without Limits or Throttling) and `CWE-400` (Uncontrolled Resource Consumption). This should not be rated Low because the affected resource is shared GPU memory in the serving path and the code already treats the PyNv decoder/CUDA-context footprint as large enough to reserve at startup when statically configured.\n\nLimitations: exploitation requires a GPU deployment where PyNvVideoCodec is installed and usable, and the request must reach a video-capable model/path. The issue does not claim code execution, data disclosure, or SSRF.\n\n## Suggested Fix\n\nDo not allow untrusted request fields to select a GPU decoder that was not included in startup memory reservation. The simplest fix is to reject request-level `media_io_kwargs.video.video_backend=\"pynvvideocodec\"` unless the static server configuration already selected PyNvVideoCodec and reserved its decoder/CUDA-context budget.\n\nIf dynamic backend selection remains supported, split software and GPU decoder policies: allow request selection among CPU/software decoders only, require an explicit operator allowlist for GPU decoders, and include every request-selectable GPU decoder in the startup reservation predicate. Add regression coverage for static OpenCV startup config plus request-level PyNvVideoCodec override, and preserve the negative control where static PyNvVideoCodec configuration reserves decoder/CUDA-context bytes.\n\n## Affected Package/Versions\n\nPackage: `vllm` from `vllm-project/vllm`.\n\nConfirmed affected: current `main` at `ddd3855a28a561a5bb54d380c6e6b8b1e883cc4a`.\n\nIntroduced by: `af16446bf39de047ab57649c933063cf1cbf1e50`, `Vram semaphore infra (#44465)`, committed 2026-06-26T17:32:51-07:00.\n\nRelease status checked: `git tag --contains af16446bf` returned no release tags in the fresh checkout. GitHub repository metadata reported latest published release `v0.23.0` published 2026-06-15T05:27:20Z; the local `v0.24.0` tag also does not contain the introducing commit. The affected range should therefore be current `main` builds containing `af16446bf` until fixed, rather than a confirmed released-version range.\n\n## Advisory History\n\nPublic vLLM advisories checked included audio decompression-bomb DoS, unbounded `video/jpeg` frame-count DoS, MediaConnector SSRF, video processing RCE, multimodal embedding DoS/RCE, GGUF GPU memory exposure, multimodal hashing, and other request-parameter DoS classes. None matched request-selected PyNvVideoCodec or the static VRAM reservation mismatch.\n\nPrior local/private vLLM report families checked included request-level `media_io_kwargs` reopening `video/jpeg` frame fanout, GLM video metadata amplification, and audio media decode duration-limit bypass. Those reports share the request-level media kwargs boundary, but they target CPU/media decode limits or model metadata amplification. This report targets a different privileged asset and fix surface: GPU decoder selection after engine startup memory reservation.\n\nFocused GitHub issue/PR searches for `pynvvideocodec`, `mm_ipc_gpu_memory`, `video_backend media_io_kwargs`, `Vram semaphore infra`, and `frontend multimodal GPU decoding` found the PyNvVideoCodec zero-copy RFC, an old do-not-review prototype, merged PR `#44465`, and an unrelated TorchCodec backend PR. No public issue or PR described this security boundary.\n\n## Appendix: Bounded Source-Level Check\n\n```python\n#!/usr/bin/env python3\nfrom __future__ import annotations\n\nimport argparse\nimport json\nimport re\nimport subprocess\nfrom pathlib import Path\n\nMIB = 1024 * 1024\nGIB = 1024 * MIB\n\ndef read(repo: Path, rel: str) -\u003e str:\n return (repo / rel).read_text(encoding=\"utf-8\")\n\ndef const_int(source: str, name: str) -\u003e int:\n expr = re.search(rf\"^{name}\\s*=\\s*(.+)$\", source, flags=re.MULTILINE).group(1).strip()\n if expr == \"128 * MiB_bytes\":\n return 128 * MIB\n if expr == \"int(1.8 * 1024 * MiB_bytes)\":\n return int(1.8 * 1024 * MIB)\n if expr == \"1\":\n return 1\n raise AssertionError(expr)\n\ndef uses_pynv_static(static_media_io_kwargs: dict[str, dict[str, str]], env_backend: str) -\u003e bool:\n video_kwargs = static_media_io_kwargs.get(\"video\", {})\n video_loader_backend = video_kwargs.get(\"video_backend\") or env_backend\n codec_backend = video_kwargs.get(\"backend\")\n return video_loader_backend == \"pynvvideocodec\" or codec_backend == \"pynvvideocodec\"\n\ndef reserve_bytes(static_media_io_kwargs, env_backend, mm_ipc_gpu_memory_gb, decoder_bytes, cuda_context_bytes, retained_decoders):\n raw_frame_reserved_bytes = int(mm_ipc_gpu_memory_gb * GIB)\n per_server_decoder_bytes = decoder_bytes * retained_decoders + cuda_context_bytes\n decoder_reserved_bytes = per_server_decoder_bytes if uses_pynv_static(static_media_io_kwargs, env_backend) else 0\n return raw_frame_reserved_bytes + decoder_reserved_bytes\n\nparser = argparse.ArgumentParser()\nparser.add_argument(\"--repo\", required=True, type=Path)\nrepo = parser.parse_args().repo.resolve()\n\nmedia_video = read(repo, \"vllm/multimodal/media/video.py\")\nconnector = read(repo, \"vllm/multimodal/media/connector.py\")\nchat_protocol = read(repo, \"vllm/entrypoints/openai/chat_completion/protocol.py\")\nresponses_protocol = read(repo, \"vllm/entrypoints/openai/responses/protocol.py\")\ngpu_worker = read(repo, \"vllm/v1/worker/gpu_worker.py\")\nvideo_core = read(repo, \"vllm/multimodal/video.py\")\n\nassert \"media_io_kwargs: dict[str, dict[str, Any]] | None = Field(\" in chat_protocol\nassert \"media_io_kwargs: dict[str, dict[str, Any]] | None = Field(\" in responses_protocol\nassert \u0027video_io_kwargs = dict(self.media_io_kwargs.get(\"video\", {}))\u0027 in connector\nassert \u0027if \"video_backend\" not in video_io_kwargs and (\u0027 in connector\nassert \u0027kwargs.pop(\"video_backend\", None) or envs.VLLM_VIDEO_LOADER_BACKEND\u0027 in media_video\nassert \"elif backend == PYNVVIDEOCODEC_VIDEO_BACKEND:\" in video_core\nassert \u0027video_kwargs = mm_config.media_io_kwargs.get(\"video\", {})\u0027 in gpu_worker\n\ndecoder_bytes = const_int(video_core, \"PYNVVIDEOCODEC_DECODER_GPU_MEMORY_BYTES\")\nretained_decoders = const_int(video_core, \"PYNVVIDEOCODEC_MAX_RETAINED_DECODERS\")\ncuda_context_bytes = const_int(video_core, \"PYNVVIDEOCODEC_CUDA_CONTEXT_BYTES\")\nper_server_decoder_bytes = decoder_bytes * retained_decoders + cuda_context_bytes\n\nvulnerable_static_reserved = reserve_bytes({}, \"opencv\", 0.0, decoder_bytes, cuda_context_bytes, retained_decoders)\nnegative_control_reserved = reserve_bytes({\"video\": {\"video_backend\": \"pynvvideocodec\"}}, \"opencv\", 0.0, decoder_bytes, cuda_context_bytes, retained_decoders)\nraw_frame_only_control = reserve_bytes({}, \"opencv\", 0.25, decoder_bytes, cuda_context_bytes, retained_decoders)\n\nhead = subprocess.check_output([\"git\", \"-C\", str(repo), \"rev-parse\", \"HEAD\"], text=True).strip()\nprint(json.dumps({\n \"head\": head,\n \"vulnerable\": vulnerable_static_reserved == 0 and negative_control_reserved == per_server_decoder_bytes,\n \"reservation_simulation\": {\n \"env_video_loader_backend\": \"opencv\",\n \"request_selects_pynv_after_startup\": True,\n \"vulnerable_static_reserved_bytes\": vulnerable_static_reserved,\n \"negative_control_static_pynv_reserved_bytes\": negative_control_reserved,\n \"raw_frame_only_control_reserved_bytes\": raw_frame_only_control,\n \"unreserved_decoder_bytes_when_only_request_selects_pynv\": per_server_decoder_bytes,\n },\n}, indent=2, sort_keys=True))\n```",
"id": "GHSA-8pw2-6jv3-mj5j",
"modified": "2026-09-17T17:17:40Z",
"published": "2026-09-17T17:17:39Z",
"references": [
{
"type": "WEB",
"url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-8pw2-6jv3-mj5j"
},
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2026-69147"
},
{
"type": "WEB",
"url": "https://github.com/vllm-project/vllm/pull/47259"
},
{
"type": "WEB",
"url": "https://github.com/vllm-project/vllm/commit/283893c72292ede38d277e3cd2b9b64c3e4f1dda"
},
{
"type": "WEB",
"url": "https://github.com/vllm-project/vllm/commit/ba22152096b2484faa3579624a253d54804d876d"
},
{
"type": "PACKAGE",
"url": "https://github.com/vllm-project/vllm"
},
{
"type": "WEB",
"url": "https://github.com/vllm-project/vllm/releases/tag/v0.25.0"
}
],
"schema_version": "1.4.0",
"severity": [
{
"score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H",
"type": "CVSS_V3"
}
],
"summary": "vLLM: Request-selected PyNvVideoCodec GPU decode bypasses static VRAM reservation"
}
GHSA-8Q5V-6PQQ-X66H
Vulnerability from github – Published: 2026-07-20 23:02 – Updated: 2026-07-21 17:23Executive summary
Microsoft is releasing this security advisory to provide information about a vulnerability in .NET XML Encryption (System.Security.Cryptography.Xml). This advisory also provides guidance on what developers can do to update their applications to remove this vulnerability.
A denial of service vulnerability exists in the XML encryption implementation (EncryptedXml) in .NET 8, .NET 9, and .NET 10. An attacker could exploit this vulnerability by supplying crafted encrypted XML that causes uncontrolled resource consumption, resulting in denial of service.
Announcement
Announcement for this issue can be found at https://github.com/dotnet/announcements/issues/414
CVSS Details
- Version: 3.1
- Severity: High
- Score: 7.5
- Vector:
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H - Weakness: CWE-770 (Allocation of Resources Without Limits or Throttling)
Affected Platforms
- Platforms: All
- Architectures: All
Affected Packages
The vulnerability affects any Microsoft .NET project if it uses any of affected package versions listed below
.NET 10.0
| Package name | Affected version | Patched version |
|---|---|---|
| System.Security.Cryptography.Xml | >= 10.0.0, <= 10.0.9 | 10.0.10 |
.NET 9.0
| Package name | Affected version | Patched version |
|---|---|---|
| System.Security.Cryptography.Xml | >= 9.0.0, <= 9.0.17 | 9.0.18 |
.NET 8.0
| Package name | Affected version | Patched version |
|---|---|---|
| System.Security.Cryptography.Xml | >= 8.0.0, <= 8.0.3 | 8.0.4 |
Advisory FAQ
How do I know if I am affected?
If using a package listed in affected packages, you're exposed to the vulnerability.
How do I fix the issue?
To update the System.Security.Cryptography.Xml NuGet package, use one of the following methods:
NuGet Package Manager UI in Visual Studio: - Open your project in Visual Studio. - Right-click on your project in Solution Explorer and select "Manage NuGet Packages..." or navigate to "Project > Manage NuGet Packages". - In the NuGet Package Manager window, select the "Updates" tab. This tab lists packages with available updates from your configured package sources. - Select the package(s) you wish to update. You can choose a specific version from the dropdown or update to the latest available version. - Click the "Update" button.
Using the NuGet Package Manager Console in Visual Studio: - Open your project in Visual Studio. - Navigate to "Tools > NuGet Package Manager > Package Manager Console". - To update a specific package to its latest version, use the following Update-Package command:
Update-Package -Id System.Security.Cryptography.Xml
Using the .NET CLI (Command Line Interface): - Open a terminal or command prompt in your project's directory. - To update a specific package to its latest version, use the following add package command:
dotnet add package System.Security.Cryptography.Xml
Once you have updated the nuget package reference you must recompile and deploy your application. Additionally we recommend you update your runtime and/or SDKs, but it is not necessary to patch the vulnerability.
Other Information
Reporting Security Issues
If you have found a potential security issue in a supported version of .NET, please report it to the Microsoft Security Response Center (MSRC) via the MSRC Researcher Portal. Further information can be found in the MSRC Report an Issue FAQ.
Security reports made through MSRC may qualify for the Microsoft .NET Bounty. Details of the Microsoft .NET Bounty Program including terms and conditions are at https://aka.ms/corebounty.
Support
You can ask questions about this issue on GitHub in the .NET GitHub organization. The main repos are located at https://github.com/dotnet/runtime. The Announcements repo (https://github.com/dotnet/Announcements) will contain this bulletin as an issue and will include a link to a discussion issue. You can ask questions in the linked discussion issue.
Disclaimer
The information provided in this advisory is provided "as is" without warranty of any kind. Microsoft disclaims all warranties, either express or implied, including the warranties of merchantability and fitness for a particular purpose. In no event shall Microsoft Corporation or its suppliers be liable for any damages whatsoever including direct, indirect, incidental, consequential, loss of business profits or special damages, even if Microsoft Corporation or its suppliers have been advised of the possibility of such damages. Some states do not allow the exclusion or limitation of liability for consequential or incidental damages so the foregoing limitation may not apply.
External Links
Acknowledgements
Levi Broderick with Microsoft
Revisions
V1.0 (July 14, 2026): Advisory published.
{
"affected": [
{
"database_specific": {
"last_known_affected_version_range": "\u003c= 10.0.9"
},
"package": {
"ecosystem": "NuGet",
"name": "System.Security.Cryptography.Xml"
},
"ranges": [
{
"events": [
{
"introduced": "10.0.0"
},
{
"fixed": "10.0.10"
}
],
"type": "ECOSYSTEM"
}
]
},
{
"database_specific": {
"last_known_affected_version_range": "\u003c= 9.0.17"
},
"package": {
"ecosystem": "NuGet",
"name": "System.Security.Cryptography.Xml"
},
"ranges": [
{
"events": [
{
"introduced": "9.0.0"
},
{
"fixed": "9.0.18"
}
],
"type": "ECOSYSTEM"
}
]
},
{
"database_specific": {
"last_known_affected_version_range": "\u003c= 8.0.3"
},
"package": {
"ecosystem": "NuGet",
"name": "System.Security.Cryptography.Xml"
},
"ranges": [
{
"events": [
{
"introduced": "8.0.0"
},
{
"fixed": "8.0.4"
}
],
"type": "ECOSYSTEM"
}
]
}
],
"aliases": [
"CVE-2026-50525"
],
"database_specific": {
"cwe_ids": [
"CWE-770"
],
"github_reviewed": true,
"github_reviewed_at": "2026-07-20T23:02:07Z",
"nvd_published_at": "2026-07-14T20:17:37Z",
"severity": "HIGH"
},
"details": "## Executive summary\n\nMicrosoft is releasing this security advisory to provide information about a vulnerability in .NET XML Encryption (System.Security.Cryptography.Xml). This advisory also provides guidance on what developers can do to update their applications to remove this vulnerability.\n\nA denial of service vulnerability exists in the XML encryption implementation (EncryptedXml) in .NET 8, .NET 9, and .NET 10. An attacker could exploit this vulnerability by supplying crafted encrypted XML that causes uncontrolled resource consumption, resulting in denial of service.\n\n## Announcement\n\nAnnouncement for this issue can be found at https://github.com/dotnet/announcements/issues/414\n\n## CVSS Details\n\n- **Version:** 3.1\n- **Severity:** High\n- **Score:** 7.5\n- **Vector:** `CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H`\n- **Weakness:** CWE-770 (Allocation of Resources Without Limits or Throttling)\n\n## Affected Platforms\n\n- **Platforms:** All\n- **Architectures:** All\n\n## \u003ca name=\"affected-packages\"\u003e\u003c/a\u003eAffected Packages\nThe vulnerability affects any Microsoft .NET project if it uses any of affected package versions listed below\n\n### \u003ca name=\".NET 10.0\"\u003e\u003c/a\u003e.NET 10.0\nPackage name | Affected version | Patched version\n------------ | ---------------- | -------------------------\n[System.Security.Cryptography.Xml](https://www.nuget.org/packages/System.Security.Cryptography.Xml) | \u003e= 10.0.0, \u003c= 10.0.9 | 10.0.10\n\n### \u003ca name=\".NET 9.0\"\u003e\u003c/a\u003e.NET 9.0\nPackage name | Affected version | Patched version\n------------ | ---------------- | -------------------------\n[System.Security.Cryptography.Xml](https://www.nuget.org/packages/System.Security.Cryptography.Xml) | \u003e= 9.0.0, \u003c= 9.0.17 | 9.0.18\n\n### \u003ca name=\".NET 8.0\"\u003e\u003c/a\u003e.NET 8.0\nPackage name | Affected version | Patched version\n------------ | ---------------- | -------------------------\n[System.Security.Cryptography.Xml](https://www.nuget.org/packages/System.Security.Cryptography.Xml) | \u003e= 8.0.0, \u003c= 8.0.3 | 8.0.4\n\n## Advisory FAQ\n\n### \u003ca name=\"how-affected\"\u003e\u003c/a\u003eHow do I know if I am affected?\n\nIf using a package listed in [affected packages](#affected-packages), you\u0027re exposed to the vulnerability.\n\n### \u003ca name=\"how-fix\"\u003e\u003c/a\u003eHow do I fix the issue?\n\nTo update the System.Security.Cryptography.Xml NuGet package, use one of the following methods:\n\nNuGet Package Manager UI in Visual Studio:\n- Open your project in Visual Studio.\n- Right-click on your project in Solution Explorer and select \"Manage NuGet Packages...\" or navigate to \"Project \u003e Manage NuGet Packages\".\n- In the NuGet Package Manager window, select the \"Updates\" tab. This tab lists packages with available updates from your configured package sources.\n- Select the package(s) you wish to update. You can choose a specific version from the dropdown or update to the latest available version.\n- Click the \"Update\" button.\n\nUsing the NuGet Package Manager Console in Visual Studio:\n- Open your project in Visual Studio.\n- Navigate to \"Tools \u003e NuGet Package Manager \u003e Package Manager Console\".\n- To update a specific package to its latest version, use the following Update-Package command:\n\n```Update-Package -Id System.Security.Cryptography.Xml```\n\nUsing the .NET CLI (Command Line Interface):\n- Open a terminal or command prompt in your project\u0027s directory.\n- To update a specific package to its latest version, use the following add package command:\n\n```dotnet add package System.Security.Cryptography.Xml```\n\nOnce you have updated the nuget package reference you must recompile and deploy your application. Additionally we recommend you update your runtime and/or SDKs, but it is not necessary to patch the vulnerability.\n\n## Other Information\n\n### Reporting Security Issues\n\nIf you have found a potential security issue in a supported version of .NET, please report it to the Microsoft Security Response Center (MSRC) via the [MSRC Researcher Portal](https://msrc.microsoft.com/report/vulnerability/new). Further information can be found in the MSRC [Report an Issue FAQ](https://www.microsoft.com/msrc/faqs-report-an-issue).\n\nSecurity reports made through MSRC may qualify for the Microsoft .NET Bounty. Details of the Microsoft .NET Bounty Program including terms and conditions are at https://aka.ms/corebounty.\n\n### Support\n\nYou can ask questions about this issue on GitHub in the .NET GitHub organization. The main repos are located at https://github.com/dotnet/runtime. The Announcements repo (https://github.com/dotnet/Announcements) will contain this bulletin as an issue and will include a link to a discussion issue. You can ask questions in the linked discussion issue.\n\n### Disclaimer\n\nThe information provided in this advisory is provided \"as is\" without warranty of any kind. Microsoft disclaims all warranties, either express or implied, including the warranties of merchantability and fitness for a particular purpose. In no event shall Microsoft Corporation or its suppliers be liable for any damages whatsoever including direct, indirect, incidental, consequential, loss of business profits or special damages, even if Microsoft Corporation or its suppliers have been advised of the possibility of such damages. Some states do not allow the exclusion or limitation of liability for consequential or incidental damages so the foregoing limitation may not apply.\n\n### External Links\n\n[CVE-2026-50525]( https://www.cve.org/CVERecord?id=CVE-2026-50525)\n\n### Acknowledgements\n\nLevi Broderick with Microsoft\n\n### Revisions\n\nV1.0 (July 14, 2026): Advisory published.",
"id": "GHSA-8q5v-6pqq-x66h",
"modified": "2026-07-21T17:23:40Z",
"published": "2026-07-20T23:02:07Z",
"references": [
{
"type": "WEB",
"url": "https://github.com/dotnet/runtime/security/advisories/GHSA-8q5v-6pqq-x66h"
},
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2026-50525"
},
{
"type": "WEB",
"url": "https://github.com/dotnet/announcements/issues/414"
},
{
"type": "WEB",
"url": "https://github.com/dotnet/runtime/issues/130711"
},
{
"type": "PACKAGE",
"url": "https://github.com/dotnet/runtime"
},
{
"type": "WEB",
"url": "https://msrc.microsoft.com/update-guide/vulnerability/CVE-2026-50525"
}
],
"schema_version": "1.4.0",
"severity": [
{
"score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H",
"type": "CVSS_V3"
}
],
"summary": "Microsoft Security Advisory CVE-2026-50525 \u2013 .NET Denial of Service Vulnerability"
}
GHSA-8Q93-326V-3M7G
Vulnerability from github – Published: 2026-05-14 16:18 – Updated: 2026-06-09 10:18Impact
Local authenticated users can cause Synapse to starve other requests of CPU and lead to other requests failing, causing other users to be denied service.
Homeservers that trust all their local users are not at risk.
Patches
Update to Synapse 1.152.1 or later.
Workarounds
If Synapse is deployed behind a reverse proxy, the reverse proxy could be configured to limit the rate of user requests, preventing or increasing the difficulty of the attack.
Identifiers
- ELEMENTSEC-2026-1706
For more information
If you have any questions or comments about this advisory, please email us at security at element.io.
{
"affected": [
{
"package": {
"ecosystem": "PyPI",
"name": "matrix-synapse"
},
"ranges": [
{
"events": [
{
"introduced": "0"
},
{
"fixed": "1.152.1"
}
],
"type": "ECOSYSTEM"
}
]
}
],
"aliases": [
"CVE-2026-45078"
],
"database_specific": {
"cwe_ids": [
"CWE-400",
"CWE-770"
],
"github_reviewed": true,
"github_reviewed_at": "2026-05-14T16:18:40Z",
"nvd_published_at": "2026-05-28T17:16:31Z",
"severity": "HIGH"
},
"details": "### Impact\n\nLocal authenticated users can cause Synapse to starve other requests of CPU and lead to other requests failing, causing other users to be denied service.\n\nHomeservers that trust all their local users are not at risk.\n\n### Patches\n\nUpdate to Synapse 1.152.1 or later.\n\n### Workarounds\n\nIf Synapse is deployed behind a reverse proxy, the reverse proxy could be configured to limit the rate of user requests,\npreventing or increasing the difficulty of the attack.\n\n### Identifiers\n\n- ELEMENTSEC-2026-1706\n\n### For more information\n\nIf you have any questions or comments about this advisory, please email us at [security at element.io](mailto:security@element.io).",
"id": "GHSA-8q93-326v-3m7g",
"modified": "2026-06-09T10:18:03Z",
"published": "2026-05-14T16:18:40Z",
"references": [
{
"type": "WEB",
"url": "https://github.com/element-hq/synapse/security/advisories/GHSA-8q93-326v-3m7g"
},
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2026-45078"
},
{
"type": "WEB",
"url": "https://github.com/element-hq/synapse/issues/19394"
},
{
"type": "WEB",
"url": "https://github.com/element-hq/synapse/commit/3f58bc50dfba5768ee43ce48c5e74c25ba0b078a"
},
{
"type": "PACKAGE",
"url": "https://github.com/element-hq/synapse"
},
{
"type": "WEB",
"url": "https://github.com/pypa/advisory-database/tree/main/vulns/matrix-synapse/PYSEC-2026-191.yaml"
}
],
"schema_version": "1.4.0",
"severity": [
{
"score": "CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H",
"type": "CVSS_V3"
},
{
"score": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N",
"type": "CVSS_V4"
}
],
"summary": "Synapse CPU starvation (Denial of Service)"
}
GHSA-8QPC-6RXX-4PXF
Vulnerability from github – Published: 2026-09-22 00:30 – Updated: 2026-09-22 00:30vLLM through 0.29.0 contains a denial of service vulnerability in P2P KV offloading when OffloadingConnector is configured with TieringOffloadingSpec and a peer-to-peer secondary tier. Attackers can supply arbitrary remote host and port values in kv_transfer_params to create unreachable peer sessions that retain ZeroMQ sockets until the context quota is exhausted, causing an uncaught ZMQError that crashes EngineCore and stops all inference.
{
"affected": [],
"aliases": [
"CVE-2026-94624"
],
"database_specific": {
"cwe_ids": [
"CWE-770"
],
"github_reviewed": false,
"github_reviewed_at": null,
"nvd_published_at": "2026-09-21T22:17:01Z",
"severity": "HIGH"
},
"details": "vLLM through 0.29.0 contains a denial of service vulnerability in P2P KV offloading when OffloadingConnector is configured with TieringOffloadingSpec and a peer-to-peer secondary tier. Attackers can supply arbitrary remote host and port values in kv_transfer_params to create unreachable peer sessions that retain ZeroMQ sockets until the context quota is exhausted, causing an uncaught ZMQError that crashes EngineCore and stops all inference.",
"id": "GHSA-8qpc-6rxx-4pxf",
"modified": "2026-09-22T00:30:55Z",
"published": "2026-09-22T00:30:55Z",
"references": [
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2026-94624"
},
{
"type": "WEB",
"url": "https://github.com/vllm-project/vllm/pull/51504"
},
{
"type": "WEB",
"url": "https://github.com/vllm-project/vllm"
},
{
"type": "WEB",
"url": "https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/v1/kv_offload/tiering/p2p/control/zmq.py#L240-L260"
},
{
"type": "WEB",
"url": "https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/v1/kv_offload/tiering/p2p/manager.py#L667-L677"
},
{
"type": "WEB",
"url": "https://www.vulncheck.com/advisories/vllm-through-0.29.0-denial-of-service-via-unbounded-p2p-kv-offloading-sessions"
}
],
"schema_version": "1.4.0",
"severity": [
{
"score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H",
"type": "CVSS_V3"
},
{
"score": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X",
"type": "CVSS_V4"
}
]
}
GHSA-8R5W-FX9Q-RH85
Vulnerability from github – Published: 2022-05-13 01:05 – Updated: 2022-05-13 01:05On EX2300, EX3400, EX4600, QFX3K and QFX5K series, firewall filter configuration cannot perform packet matching on any IPv6 extension headers. This issue may allow IPv6 packets that should have been blocked to be forwarded. IPv4 packet filtering is unaffected by this vulnerability. Affected releases are Juniper Networks Junos OS on EX and QFX series;: 14.1X53 versions prior to 14.1X53-D47; 15.1 versions prior to 15.1R7; 15.1X53 versions prior to 15.1X53-D234 on QFX5200/QFX5110 series; 15.1X53 versions prior to 15.1X53-D591 on EX2300/EX3400 series; 16.1 versions prior to 16.1R7; 17.1 versions prior to 17.1R2-S10, 17.1R3; 17.2 versions prior to 17.2R3; 17.3 versions prior to 17.3R3; 17.4 versions prior to 17.4R2; 18.1 versions prior to 18.1R2.
{
"affected": [],
"aliases": [
"CVE-2019-0005"
],
"database_specific": {
"cwe_ids": [
"CWE-770"
],
"github_reviewed": false,
"github_reviewed_at": null,
"nvd_published_at": "2019-01-15T21:29:00Z",
"severity": "MODERATE"
},
"details": "On EX2300, EX3400, EX4600, QFX3K and QFX5K series, firewall filter configuration cannot perform packet matching on any IPv6 extension headers. This issue may allow IPv6 packets that should have been blocked to be forwarded. IPv4 packet filtering is unaffected by this vulnerability. Affected releases are Juniper Networks Junos OS on EX and QFX series;: 14.1X53 versions prior to 14.1X53-D47; 15.1 versions prior to 15.1R7; 15.1X53 versions prior to 15.1X53-D234 on QFX5200/QFX5110 series; 15.1X53 versions prior to 15.1X53-D591 on EX2300/EX3400 series; 16.1 versions prior to 16.1R7; 17.1 versions prior to 17.1R2-S10, 17.1R3; 17.2 versions prior to 17.2R3; 17.3 versions prior to 17.3R3; 17.4 versions prior to 17.4R2; 18.1 versions prior to 18.1R2.",
"id": "GHSA-8r5w-fx9q-rh85",
"modified": "2022-05-13T01:05:20Z",
"published": "2022-05-13T01:05:20Z",
"references": [
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2019-0005"
},
{
"type": "WEB",
"url": "https://kb.juniper.net/JSA10905"
},
{
"type": "WEB",
"url": "http://www.securityfocus.com/bid/106665"
}
],
"schema_version": "1.4.0",
"severity": [
{
"score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:N",
"type": "CVSS_V3"
}
]
}
Mitigation
Clearly specify the minimum and maximum expectations for capabilities, and dictate which behaviors are acceptable when resource allocation reaches limits.
Mitigation
Limit the amount of resources that are accessible to unprivileged users. Set per-user limits for resources. Allow the system administrator to define these limits. Be careful to avoid CWE-410.
Mitigation
Design throttling mechanisms into the system architecture. The best protection is to limit the amount of resources that an unauthorized user can cause to be expended. A strong authentication and access control model will help prevent such attacks from occurring in the first place, and it will help the administrator to identify who is committing the abuse. The login application should be protected against DoS attacks as much as possible. Limiting the database access, perhaps by caching result sets, can help minimize the resources expended. To further limit the potential for a DoS attack, consider tracking the rate of requests received from users and blocking requests that exceed a defined rate threshold.
Mitigation MIT-5
Strategy: Input Validation
- Assume all input is malicious. Use an "accept known good" input validation strategy, i.e., use a list of acceptable inputs that strictly conform to specifications. Reject any input that does not strictly conform to specifications, or transform it into something that does.
- When performing input validation, consider all potentially relevant properties, including length, type of input, the full range of acceptable values, missing or extra inputs, syntax, consistency across related fields, and conformance to business rules. As an example of business rule logic, "boat" may be syntactically valid because it only contains alphanumeric characters, but it is not valid if the input is only expected to contain colors such as "red" or "blue."
- Do not rely exclusively on looking for malicious or malformed inputs. This is likely to miss at least one undesirable input, especially if the code's environment changes. This can give attackers enough room to bypass the intended validation. However, denylists can be useful for detecting potential attacks or determining which inputs are so malformed that they should be rejected outright.
Mitigation MIT-15
For any security checks that are performed on the client side, ensure that these checks are duplicated on the server side, in order to avoid CWE-602. Attackers can bypass the client-side checks by modifying values after the checks have been performed, or by changing the client to remove the client-side checks entirely. Then, these modified values would be submitted to the server.
Mitigation
- Mitigation of resource exhaustion attacks requires that the target system either:
- The first of these solutions is an issue in itself though, since it may allow attackers to prevent the use of the system by a particular valid user. If the attacker impersonates the valid user, they may be able to prevent the user from accessing the server in question.
- The second solution can be difficult to effectively institute -- and even when properly done, it does not provide a full solution. It simply requires more resources on the part of the attacker.
- recognizes the attack and denies that user further access for a given amount of time, typically by using increasing time delays
- uniformly throttles all requests in order to make it more difficult to consume resources more quickly than they can again be freed.
Mitigation
Ensure that protocols have specific limits of scale placed on them.
Mitigation MIT-38.1
- If the program must fail, ensure that it fails gracefully (fails closed). There may be a temptation to simply let the program fail poorly in cases such as low memory conditions, but an attacker may be able to assert control before the software has fully exited. Alternately, an uncontrolled failure could cause cascading problems with other downstream components; for example, the program could send a signal to a downstream process so the process immediately knows that a problem has occurred and has a better chance of recovery.
- Ensure that all failures in resource allocation place the system into a safe posture.
Mitigation MIT-47
Strategy: Resource Limitation
- Use quotas or other resource-limiting settings provided by the operating system or environment. For example, when managing system resources in POSIX, setrlimit() can be used to set limits for certain types of resources, and getrlimit() can determine how many resources are available. However, these functions are not available on all operating systems.
- When the current levels get close to the maximum that is defined for the application (see CWE-770), then limit the allocation of further resources to privileged users; alternately, begin releasing resources for less-privileged users. While this mitigation may protect the system from attack, it will not necessarily stop attackers from adversely impacting other users.
- Ensure that the application performs the appropriate error checks and error handling in case resources become unavailable (CWE-703).
CAPEC-125: Flooding
An adversary consumes the resources of a target by rapidly engaging in a large number of interactions with the target. This type of attack generally exposes a weakness in rate limiting or flow. When successful this attack prevents legitimate users from accessing the service and can cause the target to crash. This attack differs from resource depletion through leaks or allocations in that the latter attacks do not rely on the volume of requests made to the target but instead focus on manipulation of the target's operations. The key factor in a flooding attack is the number of requests the adversary can make in a given period of time. The greater this number, the more likely an attack is to succeed against a given target.
CAPEC-130: Excessive Allocation
An adversary causes the target to allocate excessive resources to servicing the attackers' request, thereby reducing the resources available for legitimate services and degrading or denying services. Usually, this attack focuses on memory allocation, but any finite resource on the target could be the attacked, including bandwidth, processing cycles, or other resources. This attack does not attempt to force this allocation through a large number of requests (that would be Resource Depletion through Flooding) but instead uses one or a small number of requests that are carefully formatted to force the target to allocate excessive resources to service this request(s). Often this attack takes advantage of a bug in the target to cause the target to allocate resources vastly beyond what would be needed for a normal request.
CAPEC-147: XML Ping of the Death
An attacker initiates a resource depletion attack where a large number of small XML messages are delivered at a sufficiently rapid rate to cause a denial of service or crash of the target. Transactions such as repetitive SOAP transactions can deplete resources faster than a simple flooding attack because of the additional resources used by the SOAP protocol and the resources necessary to process SOAP messages. The transactions used are immaterial as long as they cause resource utilization on the target. In other words, this is a normal flooding attack augmented by using messages that will require extra processing on the target.
CAPEC-197: Exponential Data Expansion
An adversary submits data to a target application which contains nested exponential data expansion to produce excessively large output. Many data format languages allow the definition of macro-like structures that can be used to simplify the creation of complex structures. However, this capability can be abused to create excessive demands on a processor's CPU and memory. A small number of nested expansions can result in an exponential growth in demands on memory.
CAPEC-229: Serialized Data Parameter Blowup
This attack exploits certain serialized data parsers (e.g., XML, YAML, etc.) which manage data in an inefficient manner. The attacker crafts an serialized data file with multiple configuration parameters in the same dataset. In a vulnerable parser, this results in a denial of service condition where CPU resources are exhausted because of the parsing algorithm. The weakness being exploited is tied to parser implementation and not language specific.
CAPEC-230: Serialized Data with Nested Payloads
Applications often need to transform data in and out of a data format (e.g., XML and YAML) by using a parser. It may be possible for an adversary to inject data that may have an adverse effect on the parser when it is being processed. Many data format languages allow the definition of macro-like structures that can be used to simplify the creation of complex structures. By nesting these structures, causing the data to be repeatedly substituted, an adversary can cause the parser to consume more resources while processing, causing excessive memory consumption and CPU utilization.
CAPEC-231: Oversized Serialized Data Payloads
An adversary injects oversized serialized data payloads into a parser during data processing to produce adverse effects upon the parser such as exhausting system resources and arbitrary code execution.
CAPEC-469: HTTP DoS
An attacker performs flooding at the HTTP level to bring down only a particular web application rather than anything listening on a TCP/IP connection. This denial of service attack requires substantially fewer packets to be sent which makes DoS harder to detect. This is an equivalent of SYN flood in HTTP. The idea is to keep the HTTP session alive indefinitely and then repeat that hundreds of times. This attack targets resource depletion weaknesses in web server software. The web server will wait to attacker's responses on the initiated HTTP sessions while the connection threads are being exhausted.
CAPEC-482: TCP Flood
An adversary may execute a flooding attack using the TCP protocol with the intent to deny legitimate users access to a service. These attacks exploit the weakness within the TCP protocol where there is some state information for the connection the server needs to maintain. This often involves the use of TCP SYN messages.
CAPEC-486: UDP Flood
An adversary may execute a flooding attack using the UDP protocol with the intent to deny legitimate users access to a service by consuming the available network bandwidth. Additionally, firewalls often open a port for each UDP connection destined for a service with an open UDP port, meaning the firewalls in essence save the connection state thus the high packet nature of a UDP flood can also overwhelm resources allocated to the firewall. UDP attacks can also target services like DNS or VoIP which utilize these protocols. Additionally, due to the session-less nature of the UDP protocol, the source of a packet is easily spoofed making it difficult to find the source of the attack.
CAPEC-487: ICMP Flood
An adversary may execute a flooding attack using the ICMP protocol with the intent to deny legitimate users access to a service by consuming the available network bandwidth. A typical attack involves a victim server receiving ICMP packets at a high rate from a wide range of source addresses. Additionally, due to the session-less nature of the ICMP protocol, the source of a packet is easily spoofed making it difficult to find the source of the attack.
CAPEC-488: HTTP Flood
An adversary may execute a flooding attack using the HTTP protocol with the intent to deny legitimate users access to a service by consuming resources at the application layer such as web services and their infrastructure. These attacks use legitimate session-based HTTP GET requests designed to consume large amounts of a server's resources. Since these are legitimate sessions this attack is very difficult to detect.
CAPEC-489: SSL Flood
An adversary may execute a flooding attack using the SSL protocol with the intent to deny legitimate users access to a service by consuming all the available resources on the server side. These attacks take advantage of the asymmetric relationship between the processing power used by the client and the processing power used by the server to create a secure connection. In this manner the attacker can make a large number of HTTPS requests on a low provisioned machine to tie up a disproportionately large number of resources on the server. The clients then continue to keep renegotiating the SSL connection. When multiplied by a large number of attacking machines, this attack can result in a crash or loss of service to legitimate users.
CAPEC-490: Amplification
An adversary may execute an amplification where the size of a response is far greater than that of the request that generates it. The goal of this attack is to use a relatively few resources to create a large amount of traffic against a target server. To execute this attack, an adversary send a request to a 3rd party service, spoofing the source address to be that of the target server. The larger response that is generated by the 3rd party service is then sent to the target server. By sending a large number of initial requests, the adversary can generate a tremendous amount of traffic directed at the target. The greater the discrepancy in size between the initial request and the final payload delivered to the target increased the effectiveness of this attack.
CAPEC-491: Quadratic Data Expansion
An adversary exploits macro-like substitution to cause a denial of service situation due to excessive memory being allocated to fully expand the data. The result of this denial of service could cause the application to freeze or crash. This involves defining a very large entity and using it multiple times in a single entity substitution. CAPEC-197 is a similar attack pattern, but it is easier to discover and defend against. This attack pattern does not perform multi-level substitution and therefore does not obviously appear to consume extensive resources.
CAPEC-493: SOAP Array Blowup
An adversary may execute an attack on a web service that uses SOAP messages in communication. By sending a very large SOAP array declaration to the web service, the attacker forces the web service to allocate space for the array elements before they are parsed by the XML parser. The attacker message is typically small in size containing a large array declaration of say 1,000,000 elements and a couple of array elements. This attack targets exhaustion of the memory resources of the web service.
CAPEC-494: TCP Fragmentation
An adversary may execute a TCP Fragmentation attack against a target with the intention of avoiding filtering rules of network controls, by attempting to fragment the TCP packet such that the headers flag field is pushed into the second fragment which typically is not filtered.
CAPEC-495: UDP Fragmentation
An attacker may execute a UDP Fragmentation attack against a target server in an attempt to consume resources such as bandwidth and CPU. IP fragmentation occurs when an IP datagram is larger than the MTU of the route the datagram has to traverse. Typically the attacker will use large UDP packets over 1500 bytes of data which forces fragmentation as ethernet MTU is 1500 bytes. This attack is a variation on a typical UDP flood but it enables more network bandwidth to be consumed with fewer packets. Additionally it has the potential to consume server CPU resources and fill memory buffers associated with the processing and reassembling of fragmented packets.
CAPEC-496: ICMP Fragmentation
An attacker may execute a ICMP Fragmentation attack against a target with the intention of consuming resources or causing a crash. The attacker crafts a large number of identical fragmented IP packets containing a portion of a fragmented ICMP message. The attacker these sends these messages to a target host which causes the host to become non-responsive. Another vector may be sending a fragmented ICMP message to a target host with incorrect sizes in the header which causes the host to hang.
CAPEC-528: XML Flood
An adversary may execute a flooding attack using XML messages with the intent to deny legitimate users access to a web service. These attacks are accomplished by sending a large number of XML based requests and letting the service attempt to parse each one. In many cases this type of an attack will result in a XML Denial of Service (XDoS) due to an application becoming unstable, freezing, or crashing.