video-podcast-maker

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

• Third-party content exposure detected (high risk: 0.75). At runtime, the workflow can ingest outsider-authored free text from podcast.txt (user-provided topic/script) into the agent’s LLM context via the LLM-driven steps that generate podcast.txt and subsequent beat/TTS planning; this is not a bundled reference and is not authored by the operating user’s organization.