tavily

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • Indirect Prompt Injection (LOW): The skill ingests untrusted data from web search results and external URLs. Ingestion points: Tavily API search results and extract.mjs URL content. Boundary markers: None specified in documentation. Capability inventory: Network access for search and extraction. Sanitization: Not specified in the provided files.
  • Command Execution (SAFE): The skill executes its own internal scripts using Node.js for its core functionality, which is standard behavior for this type of extension.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 01:50 PM