find-skills

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

• Third-party content exposure detected (high risk: 0.75). The required runtime workflow for this skill is to run the Skills CLI (npx skills find ...) / browse skills from the open skills ecosystem, which fetches public web/GitHub content and free-form skill metadata at runtime that can include outsider-authored text, and that text is then ingested into the agent’s LLM context for recommendation.