find-skills
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to run the
npxutility to interact with the skills CLI for searching, installing, and updating modular packages. - [EXTERNAL_DOWNLOADS]: The skill enables downloading external code from remote sources like GitHub and the skills.sh registry using the
npx skills addcommand. - [REMOTE_CODE_EXECUTION]: The core functionality of the skill is to install and enable the execution of third-party modular skills on the host system to expand agent capabilities.
- [COMMAND_EXECUTION]: Installation instructions incorporate the
-yflag, which allows for the automatic deployment of skills by bypassing manual confirmation prompts. - [PROMPT_INJECTION]: The skill contains an attack surface for indirect prompt injection by directly incorporating user-provided search queries and package names into shell commands.
- Ingestion points: User-supplied input for queries and package identifiers in SKILL.md.
- Boundary markers: No specific delimiters or safety warnings are provided for the command arguments.
- Capability inventory: Execution of shell commands via
npxfor skill management. - Sanitization: No input validation or sanitization logic is specified for the interpolated user data.
Audit Metadata