ai-content-pipeline

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow explicitly includes using a public search assistant ("Tavily Search" in Pattern 3 and Pipeline Building Blocks) and a "Blog to Video Pipeline" that ingests "", indicating the agent is expected to fetch and summarize public/untrusted web or blog content which then drives downstream actions (scripts, TTS, avatar/video generation), enabling indirect prompt injection.