find-skills

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

• Third-party content exposure detected (high risk: 0.90). This skill directs the agent to search and install skills from public sources (e.g., skills.sh and GitHub via npx skills find / npx skills add) so it will fetch and act on untrusted, user-generated third-party content that can change agent behavior, as described in SKILL.md.