LOW · 3.7

CVE-2026-26013

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 w...

Vulnerability 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 Score

3.7

LOW

CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:L
Attack Vector
NETWORK
Attack Complexity
HIGH
Privileges Required
NONE
User Interaction
NONE
Scope
UNCHANGED
Confidentiality
NONE
Integrity
NONE
Availability
LOW

Affected Products

VendorProductVersions
LangchainLangchain Core< 1.2.11

Related Weaknesses (CWE)

References

FAQ

What is CVE-2026-26013?

CVE-2026-26013 is a vulnerability with a CVSS score of 3.7 (LOW). 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 w...

How severe is CVE-2026-26013?

CVE-2026-26013 has been rated LOW with a CVSS base score of 3.7/10. Review the CVSS metrics above for detailed severity breakdown.

Is there a patch for CVE-2026-26013?

Check the references section above for vendor advisories and patch information. Affected products include: Langchain Langchain Core.