Skills
skills/firecrawl/ai-research-skills/faiss/Gen Agent Trust Hub

faiss

Warn

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: MEDIUMREMOTE_CODE_EXECUTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The LangChain integration example in SKILL.md uses the allow_dangerous_deserialization=True flag when calling FAISS.load_local. This setting enables the use of Python's pickle module to load index data. If an agent or user uses this code to load a FAISS index provided by an untrusted source, it can lead to arbitrary code execution on the host system.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 28, 2026, 06:06 PM