happyhorse
Warn
Audited by Snyk on May 18, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The SKILL.md examples and parameter docs explicitly show passing arbitrary external URLs for "first_frame", "reference_images", and "video" (e.g., I2V/R2V/Video Edit examples), which the CLI/app will fetch and consume as untrusted third-party content influencing generation/editing behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata