Server-side Request Forgery (SSRF) Affecting langchain-openai package, versions [,1.1.9)
Threat Intelligence
Snyk has a proof-of-concept or detailed explanation of how to exploit this vulnerability.
The probability is the direct output of the EPSS model, and conveys an overall sense of the threat of exploitation in the wild. The percentile measures the EPSS probability relative to all known EPSS scores. Note: This data is updated daily, relying on the latest available EPSS model version. Check out the EPSS documentation for more details.
Do your applications use this vulnerable package?
In a few clicks we can analyze your entire application and see what components are vulnerable in your application, and suggest you quick fixes.
Test your applicationsSnyk Learn
Learn about Server-side Request Forgery (SSRF) vulnerabilities in an interactive lesson.
Start learning- Snyk IDSNYK-PYTHON-LANGCHAINOPENAI-15263095
- published11 Feb 2026
- disclosed10 Feb 2026
- creditFinder16
Introduced: 10 Feb 2026
CVE-2026-26013 (opens in a new tab)How to fix?
Upgrade langchain-openai to version 1.1.9 or higher.
Overview
langchain-openai is an An integration package connecting OpenAI and LangChain
Affected versions of this package are vulnerable to Server-side Request Forgery (SSRF) via the ChatOpenAI.get_num_tokens_from_messages() function. An attacker can cause the server to make internal network requests, though they cannot see the responses, by supplying crafted image_url values in user input. The vulnerable invocation of get_num_tokens_from_messages() happens during token counting, which may happen at several points in the application's execution that are out of the control of the attacker. Small disruptions may result from exploitation, due to unintended requests being sent.