PYSEC-2026-2562

Vulnerability from pysec - Published: 2026-07-13 14:36 - Updated: 2026-07-13 16:04
VLAI
Details

Server-Side Request Forgery (SSRF) in ChatOpenAI Image Token Counting

Summary

The ChatOpenAI.get_num_tokens_from_messages() method fetches arbitrary image_url values without validation when computing token counts for vision-enabled models. This allows attackers to trigger Server-Side Request Forgery (SSRF) attacks by providing malicious image URLs in user input.

Severity

Low - The vulnerability allows SSRF attacks but has limited impact due to: - Responses are not returned to the attacker (blind SSRF) - Default 5-second timeout limits resource exhaustion - Non-image responses fail at PIL image parsing

Impact

An attacker who can control image URLs passed to get_num_tokens_from_messages() can: - Trigger HTTP requests from the application server to arbitrary internal or external URLs - Cause the server to access internal network resources (private IPs, cloud metadata endpoints) - Cause minor resource consumption through image downloads (bounded by timeout)

Note: This vulnerability occurs during token counting, which may happen outside of model invocation (e.g., in logging, metrics, or token budgeting flows).

Details

The vulnerable code path: 1. get_num_tokens_from_messages() processes messages containing image_url content blocks 2. For images without detail: "low", it calls _url_to_size() to fetch the image and compute token counts 3. _url_to_size() performs httpx.get(image_source) on any URL without validation 4. Prior to the patch, there was no SSRF protection, size limits, or explicit timeout

File: libs/partners/openai/langchain_openai/chat_models/base.py

Patches

The vulnerability has been patched in langchain-openai==1.1.9 (requires langchain-core==1.2.11).

The patch adds: 1. SSRF validation using langchain_core._security._ssrf_protection.validate_safe_url() to block: - Private IP ranges (RFC 1918, loopback, link-local) - Cloud metadata endpoints (169.254.169.254, etc.) - Invalid URL schemes 2. Explicit size limits (50 MB maximum, matching OpenAI's payload limit) 3. Explicit timeout (5 seconds, same as httpx.get default) 4. Allow disabling image fetching via allow_fetching_images=False parameter

Workarounds

If you cannot upgrade immediately:

  1. Sanitize input: Validate and filter image_url values before passing messages to token counting or model invocation
  2. Use network controls: Implement egress filtering to prevent outbound requests to private IPs
Severity
3.7 (Low)
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:L
Impacted products
Name purl
langchain-core pkg:pypi/langchain-core
Aliases
To clipboard 

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "langchain-core",
        "purl": "pkg:pypi/langchain-core"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "1.2.11"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ],
      "versions": [
        "0.0.1",
        "0.0.10",
        "0.0.11",
        "0.0.12",
        "0.0.13",
        "0.0.13rc1",
        "0.0.13rc2",
        "0.0.2",
        "0.0.3",
        "0.0.4",
        "0.0.5",
        "0.0.6",
        "0.0.7",
        "0.0.8",
        "0.0.9",
        "0.1.0",
        "0.1.1",
        "0.1.10",
        "0.1.11",
        "0.1.12",
        "0.1.12rc1",
        "0.1.13",
        "0.1.14",
        "0.1.15",
        "0.1.15rc1",
        "0.1.15rc2",
        "0.1.16",
        "0.1.17",
        "0.1.18",
        "0.1.19",
        "0.1.2",
        "0.1.20",
        "0.1.21",
        "0.1.22",
        "0.1.23",
        "0.1.24",
        "0.1.25",
        "0.1.26",
        "0.1.27",
        "0.1.28",
        "0.1.29",
        "0.1.3",
        "0.1.30",
        "0.1.31",
        "0.1.32",
        "0.1.33",
        "0.1.33rc1",
        "0.1.34",
        "0.1.35",
        "0.1.36",
        "0.1.37",
        "0.1.38",
        "0.1.39",
        "0.1.4",
        "0.1.40",
        "0.1.41",
        "0.1.42",
        "0.1.42rc1",
        "0.1.43",
        "0.1.44",
        "0.1.45",
        "0.1.46",
        "0.1.47",
        "0.1.47rc1",
        "0.1.48",
        "0.1.49",
        "0.1.5",
        "0.1.50",
        "0.1.51",
        "0.1.52",
        "0.1.53",
        "0.1.6",
        "0.1.7",
        "0.1.8",
        "0.1.9",
        "0.2.0",
        "0.2.0rc1",
        "0.2.1",
        "0.2.10",
        "0.2.11",
        "0.2.12",
        "0.2.13",
        "0.2.15",
        "0.2.16",
        "0.2.17",
        "0.2.18",
        "0.2.19",
        "0.2.2",
        "0.2.20",
        "0.2.21",
        "0.2.22",
        "0.2.23",
        "0.2.24",
        "0.2.25",
        "0.2.26",
        "0.2.27",
        "0.2.28",
        "0.2.29",
        "0.2.29rc1",
        "0.2.2rc1",
        "0.2.3",
        "0.2.30",
        "0.2.31",
        "0.2.32",
        "0.2.33",
        "0.2.34",
        "0.2.35",
        "0.2.36",
        "0.2.37",
        "0.2.38",
        "0.2.39",
        "0.2.4",
        "0.2.40",
        "0.2.41",
        "0.2.42",
        "0.2.43",
        "0.2.5",
        "0.2.6",
        "0.2.7",
        "0.2.8",
        "0.2.9",
        "0.3.0",
        "0.3.0.dev0",
        "0.3.0.dev1",
        "0.3.0.dev2",
        "0.3.0.dev3",
        "0.3.0.dev4",
        "0.3.0.dev5",
        "0.3.1",
        "0.3.10",
        "0.3.11",
        "0.3.12",
        "0.3.13",
        "0.3.14",
        "0.3.15",
        "0.3.16",
        "0.3.17",
        "0.3.18",
        "0.3.19",
        "0.3.2",
        "0.3.20",
        "0.3.21",
        "0.3.22",
        "0.3.23",
        "0.3.24",
        "0.3.25",
        "0.3.26",
        "0.3.27",
        "0.3.28",
        "0.3.29",
        "0.3.3",
        "0.3.30",
        "0.3.31",
        "0.3.32",
        "0.3.33",
        "0.3.34",
        "0.3.34rc1",
        "0.3.34rc2",
        "0.3.35",
        "0.3.36",
        "0.3.37",
        "0.3.38",
        "0.3.39",
        "0.3.4",
        "0.3.40",
        "0.3.41",
        "0.3.42",
        "0.3.43",
        "0.3.44",
        "0.3.45",
        "0.3.45rc1",
        "0.3.46",
        "0.3.47",
        "0.3.48",
        "0.3.49",
        "0.3.5",
        "0.3.50",
        "0.3.51",
        "0.3.52",
        "0.3.53",
        "0.3.54",
        "0.3.55",
        "0.3.56",
        "0.3.56rc1",
        "0.3.57",
        "0.3.58",
        "0.3.59",
        "0.3.6",
        "0.3.60",
        "0.3.61",
        "0.3.62",
        "0.3.63",
        "0.3.64",
        "0.3.65",
        "0.3.66",
        "0.3.67",
        "0.3.68",
        "0.3.69",
        "0.3.7",
        "0.3.70",
        "0.3.71",
        "0.3.72",
        "0.3.73",
        "0.3.74",
        "0.3.75",
        "0.3.76",
        "0.3.77",
        "0.3.78",
        "0.3.79",
        "0.3.8",
        "0.3.80",
        "0.3.81",
        "0.3.82",
        "0.3.83",
        "0.3.84",
        "0.3.85",
        "0.3.86",
        "0.3.9",
        "0.4.0.dev0",
        "1.0.0",
        "1.0.0a1",
        "1.0.0a2",
        "1.0.0a3",
        "1.0.0a4",
        "1.0.0a5",
        "1.0.0a6",
        "1.0.0a7",
        "1.0.0a8",
        "1.0.0rc1",
        "1.0.0rc2",
        "1.0.0rc3",
        "1.0.1",
        "1.0.2",
        "1.0.3",
        "1.0.4",
        "1.0.5",
        "1.0.6",
        "1.0.7",
        "1.1.0",
        "1.1.1",
        "1.1.2",
        "1.1.3",
        "1.2.0",
        "1.2.1",
        "1.2.10",
        "1.2.2",
        "1.2.3",
        "1.2.4",
        "1.2.5",
        "1.2.6",
        "1.2.7",
        "1.2.8",
        "1.2.9"
      ]
    }
  ],
  "aliases": [
    "CVE-2026-26013",
    "GHSA-2g6r-c272-w58r"
  ],
  "details": "## Server-Side Request Forgery (SSRF) in ChatOpenAI Image Token Counting\n\n### Summary\nThe `ChatOpenAI.get_num_tokens_from_messages()` method fetches arbitrary `image_url` values without validation when computing token counts for vision-enabled models. This allows attackers to trigger Server-Side Request Forgery (SSRF) attacks by providing malicious image URLs in user input.\n\n### Severity\n**Low** - The vulnerability allows SSRF attacks but has limited impact due to:\n- Responses are not returned to the attacker (blind SSRF)\n- Default 5-second timeout limits resource exhaustion\n- Non-image responses fail at PIL image parsing\n\n### Impact\nAn attacker who can control image URLs passed to `get_num_tokens_from_messages()` can:\n- Trigger HTTP requests from the application server to arbitrary internal or external URLs\n- Cause the server to access internal network resources (private IPs, cloud metadata endpoints)\n- Cause minor resource consumption through image downloads (bounded by timeout)\n\n**Note:** This vulnerability occurs during token counting, which may happen outside of model invocation (e.g., in logging, metrics, or token budgeting flows).\n\n### Details\nThe vulnerable code path:\n1. `get_num_tokens_from_messages()` processes messages containing `image_url` content blocks\n2. For images without `detail: \"low\"`, it calls `_url_to_size()` to fetch the image and compute token counts\n3. `_url_to_size()` performs `httpx.get(image_source)` on any URL without validation\n4. Prior to the patch, there was no SSRF protection, size limits, or explicit timeout\n\n**File:** `libs/partners/openai/langchain_openai/chat_models/base.py`\n\n### Patches\nThe vulnerability has been patched in `langchain-openai==1.1.9` (requires `langchain-core==1.2.11`).\n\nThe patch adds:\n1. **SSRF validation** using `langchain_core._security._ssrf_protection.validate_safe_url()` to block:\n   - Private IP ranges (RFC 1918, loopback, link-local)\n   - Cloud metadata endpoints (169.254.169.254, etc.)\n   - Invalid URL schemes\n2. **Explicit size limits** (50 MB maximum, matching OpenAI\u0027s payload limit)\n3. **Explicit timeout** (5 seconds, same as `httpx.get` default)\n4. **Allow disabling image fetching** via `allow_fetching_images=False` parameter\n\n### Workarounds\nIf you cannot upgrade immediately:\n\n1. **Sanitize input:** Validate and filter `image_url` values before passing messages to token counting or model invocation\n2. **Use network controls:** Implement egress filtering to prevent outbound requests to private IPs",
  "id": "PYSEC-2026-2562",
  "modified": "2026-07-13T16:04:29.846346Z",
  "published": "2026-07-13T14:36:35.874621Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/langchain-ai/langchain/security/advisories/GHSA-2g6r-c272-w58r"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-26013"
    },
    {
      "type": "WEB",
      "url": "https://github.com/langchain-ai/langchain/commit/2b4b1dc29a833d4053deba4c2b77a3848c834565"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/langchain-ai/langchain"
    },
    {
      "type": "WEB",
      "url": "https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D1.2.11"
    },
    {
      "type": "PACKAGE",
      "url": "https://pypi.org/project/langchain-core"
    },
    {
      "type": "ADVISORY",
      "url": "https://github.com/advisories/GHSA-2g6r-c272-w58r"
    }
  ],
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:L",
      "type": "CVSS_V3"
    }
  ],
  "summary": "LangChain affected by SSRF via image_url token counting in ChatOpenAI.get_num_tokens_from_messages"
}



Log in or create an account to share your comment.




Tags
Taxonomy of the tags.





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.


Detection rules are retrieved from Rulezet.