Browse / AI Framework and Platform Flaws / CVE-2026-26013
LangChain affected by SSRF via image_url token counting in ChatOpenAI.get_num_tokens_from_messages
- Class
- AI Framework and Platform Flaws (filed by a model that read the advisory)
- Technique
- Server-side request forgery
- Affected
- langchain-core (PyPI)
- CVSS
- CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:L
- EPSS
- 0.4% chance of exploitation in 30 days
How it works, in short
Token counting for chat messages fetches any image_url in the input, so a crafted URL makes the server issue requests to arbitrary hosts. (Our summary, written by a model. The source text is below.)
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:
- Sanitize input: Validate and filter
image_urlvalues before passing messages to token counting or model invocation - Use network controls: Implement egress filtering to prevent outbound requests to private IPs
References
- https://github.com/langchain-ai/langchain/security/advisories/GHSA-2g6r-c272-w58r
- https://nvd.nist.gov/vuln/detail/CVE-2026-26013
- https://github.com/langchain-ai/langchain/commit/2b4b1dc29a833d4053deba4c2b77a3848c834565
- https://github.com/langchain-ai/langchain
- https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D1.2.11
Source: GitHub Advisory Database, used under CC BY 4.0.