CVE-2026-26013

LOW EPSS 29.7%
Published Feb 10, 20264mo ago · Modified Jun 17, 20261w ago
3.7 CVSS 3.1
Low
Find Similar
Published Feb 10, 2026 4mo ago
Last Modified Jun 17, 2026 1w ago

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 Details

Base Score
3.7
Exploitability
2.2
Impact
1.4
Vector string
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

Threat Intelligence

EPSS Exploit Probability
29.7% percentile
Exploit & Patch Status
No Known Exploit
Patch Available

Weaknesses 1

CWE-918 Server-Side Request Forgery (SSRF) Validation

Affected Products 1

VendorProductVersionRange
langchainlangchain_core* <1.2.11

References 3

  • github.com https://github.com/langchain-ai/langchain/commit/2b4b1dc29a833d4053deba4c2b77a3848c834565
    Patch
  • github.com https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D1.2.11
    ProductRelease Notes
  • github.com https://github.com/langchain-ai/langchain/security/advisories/GHSA-2g6r-c272-w58r
    MitigationVendor Advisory

Remediation

  • github.com https://github.com/langchain-ai/langchain/commit/2b4b1dc29a833d4053deba4c2b77a3848c834565
    Patch