higgsfield-shotlist-director
Warn
Audited by Snyk on Aug 14, 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). The skill reads the user-provided brief/conversation (e.g., “find … dramatic shape” and “lock the Style Prefix … Custom from the conversation”) and then injects that free text into the generated global Style Prefix and per-scene prompts inside the required HTML artifact.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata