tavily-search-free
Pass
Audited by Gen Agent Trust Hub on Feb 21, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [Unverifiable Dependencies] (LOW): The skill requires
tavily-pythonandpython-dotenv. Since thetavilyorganization is not on the pre-approved trusted sources list, this is a verifiable dependency concern. The severity is lowered to LOW because these packages are standard and necessary for the skill's primary search functionality.- [Indirect Prompt Injection] (LOW): This skill retrieves content from the internet and presents it to the agent, creating a surface for indirect prompt injection. - Ingestion points:
scripts/tavily_search.py(via the Tavily API). - Boundary markers: Absent; the script returns raw JSON results without delimiters or warnings to the LLM.
- Capability inventory: The skill is designed for network communication with
api.tavily.com. - Sanitization: Absent; content from the web is passed to the agent without filtering or escaping.
Audit Metadata