CVE-2026-26013: CWE-918: Server-Side Request Forgery (SSRF) in langchain-ai langchain
A Server-Side Request Forgery (SSRF) vulnerability exists in langchain-ai's langchain framework versions prior to 1.2.11. The vulnerability occurs in the ChatOpenAI.get_num_tokens_from_messages() method, which fetches arbitrary image URLs without validation when computing token counts for vision-enabled models. This allows an attacker to supply malicious image URLs that trigger SSRF. The issue is fixed in version 1.2.11. The CVSS score is 3.
AI Analysis
Technical Summary
CVE-2026-26013 is a Server-Side Request Forgery (SSRF) vulnerability in the langchain framework before version 1.2.11. Specifically, the ChatOpenAI.get_num_tokens_from_messages() method does not validate image_url inputs when calculating token counts for vision-enabled models, allowing attackers to cause the server to make unintended HTTP requests to arbitrary URLs. This vulnerability is addressed in langchain version 1.2.11.
Potential Impact
The vulnerability allows attackers to induce the server to make arbitrary HTTP requests to internal or external systems via crafted image URLs. However, the CVSS score of 3.7 and vector indicate no impact on confidentiality or integrity, and only a low impact on availability. There are no known exploits in the wild. The impact is limited to potential SSRF-induced availability issues or network reconnaissance.
Mitigation Recommendations
Upgrade langchain to version 1.2.11 or later, where the vulnerability is fixed. Since this is an official fix, applying the update fully mitigates the issue. No additional mitigation steps are indicated.
CVE-2026-26013: CWE-918: Server-Side Request Forgery (SSRF) in langchain-ai langchain
Description
A Server-Side Request Forgery (SSRF) vulnerability exists in langchain-ai's langchain framework versions prior to 1.2.11. The vulnerability occurs in the ChatOpenAI.get_num_tokens_from_messages() method, which fetches arbitrary image URLs without validation when computing token counts for vision-enabled models. This allows an attacker to supply malicious image URLs that trigger SSRF. The issue is fixed in version 1.2.11. The CVSS score is 3.
CVSS v3.1
Score 3.7low
Affected software
Weaknesses
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
CVE-2026-26013 is a Server-Side Request Forgery (SSRF) vulnerability in the langchain framework before version 1.2.11. Specifically, the ChatOpenAI.get_num_tokens_from_messages() method does not validate image_url inputs when calculating token counts for vision-enabled models, allowing attackers to cause the server to make unintended HTTP requests to arbitrary URLs. This vulnerability is addressed in langchain version 1.2.11.
Potential Impact
The vulnerability allows attackers to induce the server to make arbitrary HTTP requests to internal or external systems via crafted image URLs. However, the CVSS score of 3.7 and vector indicate no impact on confidentiality or integrity, and only a low impact on availability. There are no known exploits in the wild. The impact is limited to potential SSRF-induced availability issues or network reconnaissance.
Mitigation Recommendations
Upgrade langchain to version 1.2.11 or later, where the vulnerability is fixed. Since this is an official fix, applying the update fully mitigates the issue. No additional mitigation steps are indicated.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- GitHub_M
- Date Reserved
- 2026-02-09T21:36:29.554Z
- Cvss Version
- 3.1
- State
- PUBLISHED
Threat ID: 698bae314b57a58fa12e3ee6
Added to database: 02/10/2026, 22:16:17 UTC
Last enriched: 06/03/2026, 21:22:47 UTC
Last updated: 09/10/2026, 19:36:53 UTC
Views: 267
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.