edit-video-blog

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

• Third-party content exposure detected (high risk: 0.80). The skill requires a user-provided video transcript (Step 0) and explicitly instructs the agent to "Read the full transcript" (Step 1) and to use the transcript as the "source of truth" when writing the article (Step 4), meaning untrusted, user-generated third‑party content will be ingested and can directly influence the agent's decisions and outputs.