Skills
skills/benedictking/benedictking-skills/tavily-web/Gen Agent Trust Hub

tavily-web

Pass

Audited by Gen Agent Trust Hub on Apr 25, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The script scripts/tavily-api.cjs connects to api.tavily.com to retrieve search results and extract content from remote websites.
  • [DATA_EXFILTRATION]: User-provided search queries and target URLs are transmitted to the Tavily API endpoints as part of the core research functionality.
  • [PROMPT_INJECTION]: The skill processes untrusted content retrieved from the web, which introduces an indirect prompt injection surface.
  • Ingestion points: Webpage content and search metadata are fetched from the Tavily API and returned to the agent context.
  • Boundary markers: None provided in the output stream.
  • Capability inventory: The skill is permitted to use Bash and Read tools.
  • Sanitization: Web content is returned as JSON-formatted text without specific filtering for embedded instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 25, 2026, 10:30 PM