faiss
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- SAFE (SAFE): No malicious instructions or suspicious patterns found. The skill serves as a guide for the FAISS library.
- INDIRECT_PROMPT_INJECTION (LOW): The LangChain integration snippet includes the parameter allow_dangerous_deserialization=True. While this is a standard requirement for loading FAISS indices in LangChain (which uses the pickle module), it poses a security risk if the index file originates from an untrusted source. This is a usage warning rather than a direct vulnerability in the skill itself.
Audit Metadata