CVE-2026-26013
Prior to 1.2.11, the ChatOpenAI.get_num_tokens_from_messages() method fetches arbitrary image_url values without validation when computing token counts for vision-enabled models.
Does this matter?
Lower severity and a low EPSS score (0.39%). Track it; it rarely justifies an emergency change on its own.
Description
LangChain is a framework for building agents and LLM-powered applications. Prior to 1.2.11, 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. This vulnerability is fixed in 1.2.11.
- CVSS 3.1
- 3.7 LOWCVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:L
- EPSS
- 0.39% probability · 33th percentile
- CISA KEV
- Not listed
- Weakness
- CWE-918
- Affected
- langchain/langchain core
- Source
- security-advisories@github.com
References
- https://github.com/langchain-ai/langchain/commit/2b4b1dc29a833d4053deba4c2b77a3848c834565Patch
- https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D1.2.11Product, Release Notes
- https://github.com/langchain-ai/langchain/security/advisories/GHSA-2g6r-c272-w58rMitigation, Vendor Advisory
Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.