tavily-web
Pass
Audited by Gen Agent Trust Hub on Apr 11, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes data from the public web.
- Ingestion points: Web search results and URL content extraction (SKILL.md).
- Boundary markers: The documentation does not specify delimiters to isolate untrusted web content from agent instructions.
- Capability inventory: Ingests and processes external web content.
- Sanitization: No sanitization or validation of retrieved content is documented.
- [EXTERNAL_DOWNLOADS]: The installation command fetches the skill from a remote repository.
- Source: BenedictKing/tavily-web.
- Method: npx skills add. This is the standard mechanism for skill deployment and is considered safe in this context.
Audit Metadata