find-skills

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 1.00). The skill's workflow explicitly directs the agent to run npx skills find and to browse/install skills from public sources like https://skills.sh/ and GitHub (npx skills add <owner/repo@skill>), meaning the agent will fetch and interpret untrusted, user-generated third-party content whose instructions could change tool use or behavior.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly instructs runtime installation of external skill packages (e.g., "npx skills add vercel-labs/agent-skills@vercel-react-best-practices" which fetches code from https://skills.sh/vercel-labs/agent-skills/vercel-react-best-practices), meaning remote content is fetched at runtime and can execute code or alter agent behavior.