tavily-map
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or persistence mechanisms were detected. The skill follows security best practices by limiting shell tool access specifically to the Tavily CLI via the allowed-tools configuration.
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external websites to map their structure. While this constitutes a surface for indirect prompt injection, it is the primary and legitimate purpose of the search tool and does not indicate malicious intent.
- Ingestion points: External website URLs processed by the tvly map command as described in SKILL.md.
- Boundary markers: Not explicitly implemented in the sample CLI commands.
- Capability inventory: Execution is limited to the tvly mapping and extraction commands.
- Sanitization: The skill relies on the underlying Tavily service and CLI to validate input URLs and sanitize discovered link data.
Audit Metadata