generate-video

Warn

Audited by Snyk on Mar 6, 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 generate-video flow explicitly calls external AI services (Nano Banana Pro / Gemini for image generation in references/image-generator.md and generator.md, and Claude for quality checks in references/image-quality-check.md) and the agent reads and acts on their text/image outputs (adopt vs. regenerate), so untrusted third-party responses are ingested and can materially influence subsequent tool actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 6, 2026, 11:18 AM