find-skills

Pass

Audited by Gen Agent Trust Hub on Sep 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the discovery and installation of external code packages from the skills.sh ecosystem using the npx skills add command. It specifically references official repositories from trusted organizations like Vercel Labs and Anthropic.
  • [COMMAND_EXECUTION]: Instructs the agent to execute shell commands via the Skills CLI, including npx skills find for discovery and npx skills add for installation.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of search results and package metadata from the open ecosystem.
  • Ingestion points: Output from the npx skills find command (SKILL.md).
  • Boundary markers: The instructions include a dedicated verification step (Step 4) requiring the agent to validate reputation markers before recommending a skill.
  • Capability inventory: The skill can execute shell commands to install and update software packages (SKILL.md).
  • Sanitization: Guidelines instruct the agent to verify install counts, GitHub stars, and source reputation (preferring known organizations) to mitigate the risk of malicious or low-quality packages.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 27, 2026, 12:29 PM