podcast-production

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

• Third-party content exposure detected (low risk: 0.10). Outsider-authored free text is only handled through user-provided editor artifacts (approved-script.md and edit-plan.json), and at runtime the LLM ingests only the explicitly provided verbatim/editorial strings from those files rather than passively consuming a public feed/inbox or auto-searched content.