tavily-entity
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external web content and user-provided files, creating an attack surface for indirect prompt injection.
- Ingestion points: The skill reads content from web pages found via search results and processes rows from user-supplied CSV files or pasted tables in SKILL.md.
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded within the external data or CSV content.
- Capability inventory: The skill utilizes shell execution for the 'tvly' tool and has the ability to write to the local file system (CSV generation).
- Sanitization: There are no explicit instructions to sanitize or escape data retrieved from external sources before it is processed or included in output files.
Audit Metadata