amazon-nova-canvas

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a technical guide for using the Amazon Bedrock InvokeModel API specifically for Nova Canvas. It includes detailed schema definitions and operational lifecycle warnings regarding model end-of-life dates.
  • [SAFE]: Authentication practices align with AWS security standards, recommending IAM roles and short-lived credentials while explicitly warning against hardcoding secrets in source code or manifests.
  • [SAFE]: The included Python script demonstrates safe coding practices, such as atomic file writes, strict Base64 decoding validation, image dimension verification, and response size capping to prevent memory exhaustion.
  • [SAFE]: All identified dependencies (boto3, Pillow) are standard, well-known libraries for the intended task. No remote code execution, obfuscation, or suspicious network patterns were found.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 01:51 PM
Security Audit — agent-trust-hub — amazon-nova-canvas