find-skills
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
npx skillscommand-line utility to interact with the skills ecosystem. This includes searching for packages and managing installations. - [EXTERNAL_DOWNLOADS]: The skill guides the agent to download and install external code packages from sources like GitHub via the
npx skills addcommand. It specifically references well-known and trusted sources for best-practice guidelines. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a potential attack surface for indirect prompt injection.
- Ingestion points: Data enters the agent's context through the output of the
npx skills findcommand, which fetches search results from external registries. - Boundary markers: Not explicitly defined for search result processing, though the workflow involves presenting options to the user before installation.
- Capability inventory: The skill can execute shell commands via
npxto install software (npx skills add). - Sanitization: The skill does not describe specific sanitization of external search results before processing.
Audit Metadata