seedance-social-commerce-video

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill explicitly documents passing an API key via --api-key and shows the sk-api-* format, which invites embedding real secret values verbatim in commands or outputs (high exfiltration risk), even though env-var/config alternatives are mentioned.

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

• Third-party content exposure detected (medium risk: 0.30). The runtime path scripts/videogen.py → cmd_video/skill_generate → client.generate_video(... prompt=args.prompt ...) ingests outsider-authored free text from the user-provided --prompt/--system and forwards it to the AI Hive generation endpoint as part of the request body.