faceless-explainer

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

• Third-party content exposure detected (medium risk: 0.30). Outsider-authored free text is ingested at runtime via Step 1, where the user’s “full input” is saved verbatim to capture/extracted/visible-text.txt and then reused in Step 3 to draft STORYBOARD.md/SCRIPT.md, which later drives audio/TTS.