tavily-web

Warn

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill's installation instructions recommend using npx skills add -g BenedictKing/tavily-web, which downloads and installs code from an unverified third-party repository.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it is designed to ingest and process untrusted data from the web.
  • Ingestion points: Web search results, content extracted from URLs, and crawled website data from the Tavily API (SKILL.md).
  • Boundary markers: The instructions do not specify any delimiters or safety markers to differentiate between user instructions and fetched web content.
  • Capability inventory: The skill performs network-based search and extraction operations.
  • Sanitization: No evidence of sanitization, filtering, or validation of the fetched external content is described.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 12, 2026, 04:11 AM
Security Audit — agent-trust-hub — tavily-web