CVE-2026-26013

low-risk
Published 2026-02-10

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.

Do I need to act?

-
0.02% chance of exploitation
EPSS score — low exploit probability
-
Not on CISA KEV list
No confirmed active exploitation reported to CISA
?
Patch status unknown
Check vendor advisories for fix availability and mitigation guidance
3
CVSS 3.7/10 Low
NETWORK / HIGH complexity

Affected Products (1)

Langchain Core

Affected Vendors

18
/ 100
low-risk
Severity 13/34 · Low
Exploitability 0/34 · Minimal
Exposure 5/34 · Minimal