seedance-prompt-zh
Warn
Audited by Snyk on May 25, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill explicitly requires ingesting and interpreting user-provided/untrusted media via the @ reference system (e.g., numerous instructions in SKILL.md like "参考 @视频1", "为每个素材指定用途", and the "交互指引" step 2 about understanding user images/videos/audio), and those referenced files directly influence generation/editing decisions, so they could carry indirect prompt injections.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata