LangChain AI LangChain

• CVE-2026-55443 Medium 5.1 LangChain: Path traversal and sandbox escape in LangChain file-search middleware and loaders 0.2%
• CVE-2026-44843 High 8.2 LangChain: Unsafe deserialization of attacker-controlled LangChain objects through overly broad `load()` allowlists 0.4%
• CVE-2026-40087 Medium 5.3 LangChain has incomplete f-string validation in prompt templates 0.3%
• CVE-2026-34070 High 7.5 LangChain Core has Path Traversal vulnerabilites in legacy `load_prompt` functions 1.4%
• CVE-2026-26013 Low 3.7 LangChain affected by SSRF via image_url token counting in ChatOpenAI.get_num_tokens_from_messages 0.4%
• CVE-2024-58340 High 8.7 LangChain <= 0.3.1 MRKLOutputParser ReDoS 0.5%
• CVE-2025-68664 Critical 9.3 LangChain serialization injection vulnerability enables secret extraction in dumps/loads APIs 42.9%
• CVE-2025-65106 High 8.3 LangChain Vulnerable to Template Injection via Attribute Access in Prompt Templates 0.5%