tavily-2

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: The skill is a standard search integration using the Tavily Search API. No malicious patterns, obfuscation, or safety bypasses were found.
  • [EXTERNAL_DOWNLOADS]: The skill requires the tavily-python package, which is the official SDK for the Tavily search service.
  • [SAFE]: Sensitive information such as API keys are managed through environment variables or user configuration, with no hardcoded credentials present in the source code.
  • [SAFE]: The skill processes external search results, which is a known data ingestion surface. 1. Ingestion points: tavily_search.py receives search results and AI-generated answers. 2. Boundary markers: The script uses clear text headers to structure the output provided to the agent. 3. Capability inventory: No dangerous subprocess calls, dynamic code execution, or file-system write operations are present in the scripts. 4. Sanitization: Results are truncated and displayed as text.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 01:12 PM