tavily

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXFILTRATION]: The skill transmits the API key to a remote service.
  • Evidence: scripts/extract.mjs and scripts/search.mjs send the TAVILY_API_KEY to https://api.tavily.com.
  • Context: This is a required operation for a well-known service associated with the skill's purpose. No sensitive local files are accessed or transmitted.
  • [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection by processing external web data.
  • Ingestion points: scripts/extract.mjs (URL extraction) and scripts/search.mjs (search results and AI-generated answers).
  • Boundary markers: Content is output directly to the console without additional delimiters.
  • Capability inventory: The skill is restricted to standard network requests and console output; it does not possess capabilities for file modification or arbitrary code execution.
  • Sanitization: Data is used as received from the API without specific sanitization for injection patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 08:02 AM