PYSEC-2026-2011

Vulnerability from pysec - Published: 2026-07-07 16:03 - Updated: 2026-07-07 17:25
VLAI
Details

Summary

A Server-Side Request Forgery (SSRF) vulnerability exists in the MediaConnector class within the vLLM project's multimodal feature set. The load_from_url and load_from_url_async methods fetch and process media from user-provided URLs without adequate restrictions on the target hosts. This allows an attacker to coerce the vLLM server into making arbitrary requests to internal network resources.

This vulnerability is particularly critical in containerized environments like llm-d, where a compromised vLLM pod could be used to scan the internal network, interact with other pods, and potentially cause denial of service or access sensitive data. For example, an attacker could make the vLLM pod send malicious requests to an internal llm-d management endpoint, leading to system instability by falsely reporting metrics like the KV cache state.

Vulnerability Details

The core of the vulnerability lies in the MediaConnector.load_from_url method and its asynchronous counterpart. These methods accept a URL string to fetch media content (images, audio, video).

https://github.com/vllm-project/vllm/blob/119f683949dfed10df769fe63b2676d7f1eb644e/vllm/multimodal/utils.py#L97-L113

The function directly processes URLs with http, https, and file schemes. An attacker can supply a URL pointing to an internal IP address or a localhost endpoint. The vLLM server will then initiate a connection to this internal resource.

  • HTTP/HTTPS Scheme: An attacker can craft a request like {"image_url": "http://127.0.0.1:8080/internal_api"}. The vLLM server will send a GET request to this internal endpoint.
  • File Scheme: The _load_file_url method attempts to restrict file access to a subdirectory defined by --allowed-local-media-path. While this is a good security measure for local file access, it does not prevent network-based SSRF attacks.

Impact in llm-d Environments

The risk is significantly amplified in orchestrated environments such as llm-d, where multiple pods communicate over an internal network.

  1. Denial of Service (DoS): An attacker could target internal management endpoints of other services within the llm-d cluster. For instance, if a monitoring or metrics service is exposed internally, an attacker could send malformed requests to it. A specific example is an attacker causing the vLLM pod to call an internal API that reports a false KV cache utilization, potentially triggering incorrect scaling decisions or even a system shutdown.

  2. Internal Network Reconnaissance: Attackers can use the vulnerability to scan the internal network for open ports and services by providing URLs like http://10.0.0.X:PORT and observing the server's response time or error messages.

  3. Interaction with Internal Services: Any unsecured internal service becomes a potential target. This could include databases, internal APIs, or other model pods that might not have robust authentication, as they are not expected to be directly exposed.

Delegating this security responsibility to an upper-level orchestrator like llm-d is problematic. The orchestrator cannot easily distinguish between legitimate requests initiated by the vLLM engine for its own purposes and malicious requests originating from user input, thus complicating traffic filtering rules and increasing management overhead.

Fix

See the --allowed-media-domains option discussed here: https://docs.vllm.ai/en/latest/usage/security.html#4-restrict-domains-access-for-media-urls

Impacted products
Name purl
vllm pkg:pypi/vllm

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "vllm",
        "purl": "pkg:pypi/vllm"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0.5.0"
            },
            {
              "fixed": "0.11.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ],
      "versions": [
        "0.10.0",
        "0.10.1",
        "0.10.1.1",
        "0.10.2",
        "0.5.0",
        "0.5.0.post1",
        "0.5.1",
        "0.5.2",
        "0.5.3",
        "0.5.3.post1",
        "0.5.4",
        "0.5.5",
        "0.6.0",
        "0.6.1",
        "0.6.1.post1",
        "0.6.1.post2",
        "0.6.2",
        "0.6.3",
        "0.6.3.post1",
        "0.6.4",
        "0.6.4.post1",
        "0.6.5",
        "0.6.6",
        "0.6.6.post1",
        "0.7.0",
        "0.7.1",
        "0.7.2",
        "0.7.3",
        "0.8.0",
        "0.8.1",
        "0.8.2",
        "0.8.3",
        "0.8.4",
        "0.8.5",
        "0.8.5.post1",
        "0.9.0",
        "0.9.0.1",
        "0.9.1",
        "0.9.2"
      ]
    }
  ],
  "aliases": [
    "CVE-2025-6242",
    "GHSA-3f6c-7fw2-ppm4"
  ],
  "details": "### Summary\n\nA Server-Side Request Forgery (SSRF) vulnerability exists in the `MediaConnector` class within the vLLM project\u0027s multimodal feature set. The `load_from_url` and `load_from_url_async` methods fetch and process media from user-provided URLs without adequate restrictions on the target hosts. This allows an attacker to coerce the vLLM server into making arbitrary requests to internal network resources.\n\nThis vulnerability is particularly critical in containerized environments like `llm-d`, where a compromised vLLM pod could be used to scan the internal network, interact with other pods, and potentially cause denial of service or access sensitive data. For example, an attacker could make the vLLM pod send malicious requests to an internal `llm-d` management endpoint, leading to system instability by falsely reporting metrics like the KV cache state.\n\n### Vulnerability Details\n\nThe core of the vulnerability lies in the `MediaConnector.load_from_url` method and its asynchronous counterpart. These methods accept a URL string to fetch media content (images, audio, video).\n\nhttps://github.com/vllm-project/vllm/blob/119f683949dfed10df769fe63b2676d7f1eb644e/vllm/multimodal/utils.py#L97-L113\n\nThe function directly processes URLs with `http`, `https`, and `file` schemes. An attacker can supply a URL pointing to an internal IP address or a `localhost` endpoint. The vLLM server will then initiate a connection to this internal resource.\n\n* **HTTP/HTTPS Scheme:** An attacker can craft a request like `{\"image_url\": \"http://127.0.0.1:8080/internal_api\"}`. The vLLM server will send a GET request to this internal endpoint.\n* **File Scheme:** The `_load_file_url` method attempts to restrict file access to a subdirectory defined by `--allowed-local-media-path`. While this is a good security measure for local file access, it does not prevent network-based SSRF attacks.\n\n### Impact in `llm-d` Environments\n\nThe risk is significantly amplified in orchestrated environments such as `llm-d`, where multiple pods communicate over an internal network.\n\n1.  **Denial of Service (DoS):** An attacker could target internal management endpoints of other services within the `llm-d` cluster. For instance, if a monitoring or metrics service is exposed internally, an attacker could send malformed requests to it. A specific example is an attacker causing the vLLM pod to call an internal API that reports a false KV cache utilization, potentially triggering incorrect scaling decisions or even a system shutdown.\n\n2.  **Internal Network Reconnaissance:** Attackers can use the vulnerability to scan the internal network for open ports and services by providing URLs like `http://10.0.0.X:PORT` and observing the server\u0027s response time or error messages.\n\n3.  **Interaction with Internal Services:** Any unsecured internal service becomes a potential target. This could include databases, internal APIs, or other model pods that might not have robust authentication, as they are not expected to be directly exposed.\n\nDelegating this security responsibility to an upper-level orchestrator like `llm-d` is problematic. **The orchestrator cannot easily distinguish between legitimate requests initiated by the vLLM engine for its own purposes and malicious requests originating from user input, thus complicating traffic filtering rules and increasing management overhead.**\n\n### Fix\n\nSee the `--allowed-media-domains` option discussed here: https://docs.vllm.ai/en/latest/usage/security.html#4-restrict-domains-access-for-media-urls",
  "id": "PYSEC-2026-2011",
  "modified": "2026-07-07T17:25:47.233697Z",
  "published": "2026-07-07T16:03:06.992470Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-3f6c-7fw2-ppm4"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2025-6242"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/commit/9d9a2b77f19f68262d5e469c4e82c0f6365ad72d"
    },
    {
      "type": "WEB",
      "url": "https://access.redhat.com/security/cve/CVE-2025-6242"
    },
    {
      "type": "WEB",
      "url": "https://bugzilla.redhat.com/show_bug.cgi?id=2373716"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/vllm-project/vllm"
    },
    {
      "type": "PACKAGE",
      "url": "https://pypi.org/project/vllm"
    },
    {
      "type": "ADVISORY",
      "url": "https://github.com/advisories/GHSA-3f6c-7fw2-ppm4"
    }
  ],
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:L/A:H",
      "type": "CVSS_V3"
    }
  ],
  "summary": "vLLM is vulnerable to Server-Side Request Forgery (SSRF) through `MediaConnector` class"
}



Log in or create an account to share your comment.




Tags
Taxonomy of the tags.


Loading…

Loading…

Loading…

Drag nodes to arrange them. Double-click a related vulnerability to open it, or a source to visit its link. The Physics button on the left tunes the layout and the simulation; the legend at the bottom left hides or shows nodes by kind and by sighting type.

Forecast uses a logistic model when the trend is rising, or an exponential decay model when the trend is falling. Fitted via linearized least squares.

Sightings

Author Source Type Date Other

Nomenclature

  • Seen: The vulnerability was mentioned, discussed, or observed by the user.
  • Confirmed: The vulnerability has been validated from an analyst's perspective.
  • Published Proof of Concept: A public proof of concept is available for this vulnerability.
  • Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
  • Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
  • Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
  • Not confirmed: The user expressed doubt about the validity of the vulnerability.
  • Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.
Vulnerability timeline

Sightings and recorded dates, grouped by day · UTC

JSON
How durations are calculated

Following the VTEM framework (Black Hat USA 2015), time to patch starts when the vendor or a coordinator was informed, total time to patch at discovery, and disclosure to patch at public disclosure; vendor response time runs from the report to its acknowledgement. Time to exploit and time unpatched start at the earliest discovery or report, falling back to public disclosure. Unpatched time ends at the first recorded patch, or the calculation time when no patch is recorded. Exploitation to patch shows the interval between those two events; a published proof of concept is a public exploit, not exploitation.

Each result shows its source dates. A negative interval means the end event came first; when date-only inputs leave the order open, the result says so. Date-only inputs are approximate. The earliest evidence wins: KEV report dates and sightings are labelled as such. Records describing another vulnerability are listed but never calculated from, and a PoC alone does not establish exploitation. Missing patch evidence does not prove that no patch exists. Filters below change the event list only.

Events included in the timeline

Loading timeline…


    Loading…

    Loading…

    Loading…

    Related by attack behaviour

    Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.