find-skills
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to use
npx skills findandnpx skills addto interact with the agent skills ecosystem. - [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of third-party agent extensions from external repositories, specifically referencing the
vercel-labsorganization on GitHub as an example source. - [INDIRECT_PROMPT_INJECTION]: The skill processes search results and package descriptions which are retrieved from an external registry.
- Ingestion points: Data returned by the
npx skills findcommand, including skill names and descriptions. - Boundary markers: The instructions provide a structured template for presenting search results to the user, helping to distinguish third-party content.
- Capability inventory: The skill possesses the ability to execute search and installation commands for software packages.
- Sanitization: The instructions do not specify a validation or sanitization step for the metadata retrieved from the package search.
Audit Metadata