web-search-tavily

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: As a web search utility, this skill retrieves content from external websites which could potentially contain malicious instructions intended to mislead or exploit the agent.
  • Ingestion points: Data enters the system via the tavilySearch function in scripts/search.ts, specifically the content, raw_content, and answer fields returned by the Tavily API.
  • Boundary markers: The output uses basic visual formatting (horizontal lines and numbering) but lacks specific instructions to the agent to treat the following data as untrusted or to ignore embedded commands.
  • Capability inventory: The script has permissions to read environment variables (TAVILY_API_KEY) and make network requests to api.tavily.com.
  • Sanitization: No filtering or sanitization of the retrieved web content is performed by the script before it is output for agent consumption.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 01:08 PM
Security Audit — agent-trust-hub — web-search-tavily