video-use

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

• Third-party content exposure detected (high risk: 0.75). Outsider free text is ingested into the LLM via the user-provided video’s outsider-authored transcript text path: transcribe*.json (from audio) → helpers/pack_transcripts.py producing edit/takes_packed.md, which the editor sub-agent reads at runtime (e.g., SKILL.md:121-131, 83-88, 112-113), and the LLM context therefore contains that transcript-derived prose.