Server-Side Request Forgery Vulnerability in LangChain Framework by LangChain AI
CVE-2026-26013

3.7LOW

Key Information:

Vendor

Langchain-ai

Status
Langchain
Vendor
CVE Published:
10 February 2026

What is CVE-2026-26013?

The LangChain framework, designed for building agents and LLM-powered applications, has a vulnerability in the ChatOpenAI.get_num_tokens_from_messages() method. This method inadequately validates image_url inputs, potentially allowing attackers to conduct Server-Side Request Forgery (SSRF) attacks by submitting malicious image URLs. This flaw can compromise the security of applications utilizing this framework. The issue has been addressed in version 1.2.11 of LangChain.

Affected Version(s)

langchain < 1.2.11

References

https://github.com/langchain-ai/langchain/security/adviso...
x_refsource_CONFIRM
https://github.com/langchain-ai/langchain/commit/2b4b1dc2...
x_refsource_MISC
https://github.com/langchain-ai/langchain/releases/tag/la...
x_refsource_MISC

CVSS V3.1

Score:
3.7
Severity:
LOW
Confidentiality:
None
Integrity:
None
Availability:
None
Attack Vector:
Network
Attack Complexity:
High
Privileges Required:
None
User Interaction:
None
Scope:
Unchanged

Timeline

  • Vulnerability published

  • Vulnerability Reserved

.