find-skills
Pass
Audited by Gen Agent Trust Hub on Jun 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Uses the 'npx skills' CLI to perform discovery, installation, and updates of agent capability packages.
- [EXTERNAL_DOWNLOADS]: Downloads skill packages from external repositories (e.g., GitHub) when the agent executes installation commands.
- [REMOTE_CODE_EXECUTION]: Facilitates the installation of external code into the agent's environment; the skill provides guidelines for the agent to verify source reputation and install counts before executing these actions.
- [PROMPT_INJECTION]: The skill processes search results from external registries, creating an indirect prompt injection surface.
- Ingestion points: Results from 'npx skills find' and 'skills.sh' are processed by the agent (SKILL.md).
- Boundary markers: No explicit delimiters are used to separate search result content from agent instructions.
- Capability inventory: The agent can execute 'npx skills add', which installs and runs external code.
- Sanitization: No automated sanitization of search result text is performed before the agent evaluates it for recommendation.
Audit Metadata