fal-video
Warn
Audited by Snyk on Feb 16, 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). This skill ingests arbitrary user-provided/untrusted images via the "input_image" file ID obtained with "refly file upload" (Execution Step 0), so the agent will read and act on third-party content supplied at runtime.
Audit Metadata