CVE-2026-26013: low-severity vulnerability in langchain-ai langchain
LangChain affected by SSRF via image_url token counting in ChatOpenAI.get_num_tokens_from_messages
Published · Updated
E-mail alert when it lands in KEV, gets a public PoC or its score goes up.
8Vexday Risk Score
No sign of exploitation. No public exploitation artifact known so far.
ssvc Trackcvss 3.7epss 0.4%
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:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:L
Affected products
langchain-ai · langchainRelated CVEs — langchain-ai langchain
In the same product, most dangerous first.
CVE-2025-68664CRITICALLangChain serialization injection vulnerability enables secret extraction in dumps/loads APIsEPSS 42.9%CVE-2026-34070HIGHLangChain Core has Path Traversal vulnerabilites in legacy `load_prompt` functionsEPSS 1.5%CVE-2025-65106HIGHLangChain Vulnerable to Template Injection via Attribute Access in Prompt TemplatesEPSS 0.5%CVE-2026-44843HIGHLangChain: Unsafe deserialization of attacker-controlled LangChain objects through overly broad `load()` allowlistsEPSS 0.4%CVE-2026-40087MEDIUMLangChain has incomplete f-string validation in prompt templatesEPSS 0.3%CVE-2026-55443MEDIUMLangChain: Path traversal and sandbox escape in LangChain file-search middleware and loadersEPSS 0.2%