Aller au contenu
3.1 Faible

CVE-2026-41488 LangChain is a framework for building agents and LLM-powered applications

Description

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 then fetched them in a separate network operation with independent DNS resolution. This left a TOCTOU / DNS rebinding window: an attacker-controlled hostname could resolve to a public IP during validation and then to a private/localhost IP during the actual fetch.

Produits et versions touchés

Produit Versions touchées Corrigé en
langchain-openai 1.1 premières → < 1.1.14 1.1.14
Suivre cette CVE