find-skills
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill is designed to facilitate the downloading and installation of external agent code and configuration files from GitHub repositories and the skills.sh registry.
- [COMMAND_EXECUTION]: The skill provides explicit instructions for the agent to execute shell commands to manage software, specifically utilizing 'npx skills find' for discovery and 'npx skills add' for installation.
- [PROMPT_INJECTION]: The skill handles untrusted external data in the form of skill search results and metadata which could contain indirect prompt injection vectors. 1. Ingestion points: The agent reads and processes output from the 'npx skills find' command which includes external repository names and descriptions. 2. Boundary markers: No delimiters or protective instructions are used to separate search results from the system context. 3. Capability inventory: The skill utilizes the 'npx skills add' command with flags to install packages globally (-g) and skip confirmation prompts (-y). 4. Sanitization: There is no evidence of filtering or sanitization performed on the external metadata before the agent presents it to the user or acts upon it.
Audit Metadata