find-skills
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
npx skillsCLI tool for its intended purpose of searching and installing agent extensions. - [EXTERNAL_DOWNLOADS]: The skill facilitates downloading components from the open agent skills ecosystem. It provides the agent with specific safety heuristics, such as checking GitHub stars and install counts, and highlights trusted organizations like Vercel Labs and Anthropic.
- [PROMPT_INJECTION]: The skill includes instructions to mitigate indirect prompt injection by requiring the agent to validate the credibility of third-party skill descriptions before processing them. Ingestion points:
npx skills findoutput in SKILL.md; Capability:npx skills addinstallation in SKILL.md; Sanitization: reputation and install count verification; Boundary markers: absent.
Audit Metadata