product-launch-video

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

• Third-party content exposure detected (high risk: 0.75). Outsider free text can enter the LLM context via Step 1’s “Explicit URL -> capture it and use the site for narration and assets” path: the captured page’s visible text is then used to draft SCRIPT.md/STORYBOARD.md in Step 3, which the agent’s LLM reads and incorporates (indirect prompt injection risk from arbitrary web content).