tiktok-content-maker

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md workflow (Phase 1, step 2) explicitly instructs the agent to "use WebFetch to scrape product detail page for additional context" when a user provides a product link, meaning the agent will ingest untrusted public web content that directly informs analysis and subsequent script-generation actions.