Skip to content
OpenAdvisories

Product · langchain-ai

langchain

8 known vulnerabilities.

All Critical High Medium Low Exploited only Public exploit

2 results · Clear filters · Feed

  • High 7.5
    CVE-2026-34070 Public exploit

    LangChain Core has Path Traversal vulnerabilites in legacy `load_prompt` functions

    LangChain is a framework for building agents and LLM-powered applications. Prior to version 1.2.22, multiple functions in langchain_core.prompts.loading read files from paths embedded in deserialized config dicts without validating against directory traversal…

    langchain-ai langchain langchain-core PyPI
  • Critical 9.3
    CVE-2025-68664 Public exploit EPSS 43%

    LangChain serialization injection vulnerability enables secret extraction in dumps/loads APIs

    LangChain is a framework for building agents and LLM-powered applications. Prior to versions 0.3.81 and 1.2.5, a serialization injection vulnerability exists in LangChain's dumps() and dumpd() functions. The functions do not escape dictionaries with 'lc' keys…

    langchain-ai langchain langchain-core PyPI