tavily-web

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The installation instructions direct users to run npx skills add -g BenedictKing/tavily-web, which fetches the skill's implementation from a community-managed GitHub repository.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because its primary function is to ingest and process untrusted content from external websites.
  • Ingestion points: Web content, search results, and crawl data retrieved from external URLs via the Tavily API (referenced in SKILL.md).
  • Boundary markers: Absent. The instructions do not define delimiters or specific warnings to prevent the agent from executing instructions potentially hidden in the fetched web content.
  • Capability inventory: The skill is designed to search, crawl, and extract content, feeding the resulting data directly into the agent's context.
  • Sanitization: Absent. There is no mention of filtering, escaping, or validating the retrieved web content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 01:23 AM
Security Audit — agent-trust-hub — tavily-web