course-creator

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

• Third-party content exposure detected (high risk: 0.90). The skill's entry-point and Phase 1 instructions (SKILL.md: "YouTube URL processing" requiring web_fetch/web_search to fetch transcripts and Phase 1 Step 6's web research of competitors) explicitly fetch and ingest public, user-generated web content which the agent must read and use to shape course modules and decisions, enabling indirect prompt injection from untrusted third-party content.