skills-catalog
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill functions as a static documentation and reference catalog for a monorepo containing various agent skills.
- [EXTERNAL_DOWNLOADS]: The documentation includes standard developer instructions for rendering a video showcase, which involves using
npm installfor theremotionframework. This is a routine operation for a user working within a local clone of the repository and does not involve automated or hidden remote code execution. - [INDIRECT_PROMPT_INJECTION]: The skill provides a catalog of 75 other skills, ingesting their descriptions into the current context. This is evaluated as safe given the static and internal nature of the documentation.
- Ingestion points:
references/skills-inventory.mdcontains descriptions for 75 skills. - Boundary markers: Data is structured in markdown tables.
- Capability inventory: This specific skill (
skills-catalog) contains no subprocess calls, network operations, or file-write capabilities. - Sanitization: None present.
Audit Metadata