SSRF in Langchain Langchain-openai
CVE-2026-41488
LangChain is a framework for building agents and LLM-powered applications. Prior to 1.1.14, langchain-openai's _url_to_size() helper (used by get_num_tokens_from_messages for image token counting) validated URLs for SSRF protection and the…
Vulnerability class: SSRF (Server-Side Request Forgery)
EPSS: 0.000 (7.8th percentile) — read the EPSS interpretation.
CVSS v3 metric
CVSS v3 base score 3.1 (Low). Vector: CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:L/I:N/A:N.
Affected products
- Langchain Langchain-openai
- Langchain-ai Langchain-openai — versions < 1.1.14
Weakness classification (CWE)
References
- https://github.com/langchain-ai/langchain/security/advisories/GHSA-r7w7-9xr2-qq2r (x_refsource_CONFIRM, Mitigation, Vendor Advisory)
Frequently asked questions
- What is CVE-2026-41488?
- CVE-2026-41488 is a low-severity vulnerability in Langchain Langchain-openai, classified under Server-Side Request Forgery (SSRF). CVSS score: 3.1/10. Published 2026-04-24.
- How severe is CVE-2026-41488?
- Low severity. CVSS v3 base score is 3.1 out of 10.