runway
Warn
Audited by Snyk on Feb 15, 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 allows ingestion of arbitrary external URLs (e.g., promptImage, videoUri, referenceImages) which the Runway API will fetch from public websites, so untrusted/user-generated third-party content can be read and influence generation, enabling indirect prompt injection.
Audit Metadata