animation-reverse-engineering

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow ingests outsider-authored free text when it downloads/probes an attacker-supplied reference URL (Phase 1 Acquire via yt-dlp/curl in dissect.sh), which then becomes LLM-readable via derived outputs (e.g., the script’s extracted frames/overview used for subsequent analysis).