higgsfield-seedance
Warn
Audited by Snyk on Aug 23, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). SKILL.md’s required runtime flow ingests the user’s free-text Seedance scene prompt directly into the preflight linter (python3 scripts/seedance_lint.py --preflight --model seedance_2_0 "") and then guides rewriting based on those filter results, so outsider-authored text is always read at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata