skill-creator-expert

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

• Third-party content exposure detected (high risk: 0.90). The skill clearly ingests untrusted public content — e.g., InteractiveSkillBuilder.extractKnowledge explicitly says it will "Scrape documentation, analyze repositories, etc.", gatherReferences uses findCommunityResources, and SkillLoader.fetchSkill/loadSkill fetches external skills — so the agent will read and interpret third‑party web/community content as part of its workflow.