seedance-video-creator
Fail
Audited by Snyk on Feb 22, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 0.90). The prompt explicitly requires using a SessionID in Authorization headers (shows curl examples with "Authorization: Bearer ${SESSION_ID}" / "Bearer your_sessionid") and instructs copying/providing the session cookie, so an agent would be expected to insert that secret verbatim into generated commands/requests — creating an exfiltration risk.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill explicitly calls the public jimeng image-generation API (/v1/images/generations) and downloads the returned IMAGE_URL (see SKILL.md and scripts/generate_video.sh), then uploads that externally-fetched image as @1 into the subsequent /v1/videos/generations request — i.e., untrusted third-party image content is ingested and directly influences subsequent model/tool behavior.
Audit Metadata