find-skills

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

• Third-party content exposure detected (high risk: 0.80). This skill explicitly directs the agent to search and install skills from public, user-authored sources (e.g., skills.sh and GitHub) using commands like "npx skills find" and "npx skills add", so the agent would read and act on untrusted third-party content (public skill metadata/repos) that can influence installation and subsequent behavior.