Vulnerability Description
LangChain is a framework for building agents and LLM-powered applications. From versions 0.3.79 and prior and 1.0.0 to 1.0.6, a template injection vulnerability exists in LangChain's prompt template system that allows attackers to access Python object internals through template syntax. This vulnerability affects applications that accept untrusted template strings (not just template variables) in ChatPromptTemplate and related prompt template classes. This issue has been patched in versions 0.3.80 and 1.0.7.
Related Weaknesses (CWE)
References
- https://github.com/langchain-ai/langchain/commit/c4b6ba254e1a49ed91f2e268e648401
- https://github.com/langchain-ai/langchain/commit/fa7789d6c21222b85211755d822ef69
- https://github.com/langchain-ai/langchain/security/advisories/GHSA-6qv9-48xg-fc7
FAQ
What is CVE-2025-65106?
CVE-2025-65106 is a documented vulnerability. LangChain is a framework for building agents and LLM-powered applications. From versions 0.3.79 and prior and 1.0.0 to 1.0.6, a template injection vulnerability exists in LangChain's prompt template s...
How severe is CVE-2025-65106?
CVSS scoring is not yet available for CVE-2025-65106. Check NVD for updates.
Is there a patch for CVE-2025-65106?
Check the references section above for vendor advisories and patch information. Review vendor security bulletins for remediation guidance.