tavily
Pass
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the
@useclawlink/clifor authentication, connecting services, and running actions.\n- [EXTERNAL_DOWNLOADS]: The skill facilitates the download and execution of the@useclawlink/clipackage from the NPM registry vianpx.\n- [PROMPT_INJECTION]: The skill processes untrusted web content through Tavily's crawl and search functions, creating a surface for indirect prompt injection.\n - Ingestion points: Data retrieved from external websites via
tavily_search,tavily_crawl, andtavily_extract(SKILL.md).\n - Boundary markers: No specific delimiters or safety instructions are defined to separate external content from agent instructions.\n
- Capability inventory: The skill can execute shell commands and perform network requests via the ClawLink CLI (SKILL.md).\n
- Sanitization: No explicit filtering or sanitization of retrieved web content is documented in the skill instructions.
Audit Metadata