find-skills

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

• Third-party content exposure detected (medium risk: 0.65). The skill’s runtime workflow is to search/browse the open agent skills ecosystem (e.g., via npx skills find / skills.sh) and then present/install matching skills, which can involve fetching outsider-authored public web content (skill listings/docs) and/or outsider-authored package metadata into the agent context.