find-scene

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill specifies that every API request must include a user API token in the JSON body (the "_token" field), which requires the agent to insert secret token values verbatim into generated requests, creating an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.80). The skill accepts and processes arbitrary public YouTube URLs via POST /api/youtube_url_to_video_source (and uses resulting videoHash/textSource in workflows like search_phrase, extract_frame, and download_by_time), which ingests untrusted, user-generated third‑party content that can materially influence subsequent tool use and decisions.