mintlify
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs a sub-agent to fetch and process external documentation from Mintlify's official website, creating a potential surface for indirect prompt injection.\n
- Ingestion points: Documentation index and markdown pages are retrieved from
https://www.mintlify.com/docs/using theWebFetchtool.\n - Boundary markers: The instructions do not define specific delimiters for external content or provide explicit warnings to the agent to ignore instructions embedded in the documentation content.\n
- Capability inventory: The skill utilizes the
Tasktool to spawn research sub-agents withreadonly: trueparameters and provides access to network resources viaWebFetch.\n - Sanitization: The instructions do not specify any validation or sanitization of the content retrieved from the external URLs.\n- [EXTERNAL_DOWNLOADS]: The skill fetches documentation and configuration index files from Mintlify's official web domain to assist with user queries regarding the platform.
Audit Metadata