ar-policy-tester
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements policy testing and validation workflows for Amazon Bedrock using the official AWS SDK (
boto3). - [SAFE]: All external communications are directed to official AWS Bedrock API endpoints for creating test cases, generating scenarios, and running test workflows.
- [SAFE]: No signs of prompt injection, data exfiltration, or unauthorized persistence were found in the skill instructions or scripts.
- [SAFE]: The skill handles user-provided text as data for API calls, which is the intended behavior for an administrative testing tool.
- [SAFE]: Dependencies are limited to standard, trusted libraries (
boto3). The use of local utility modules via relative path imports is a standard development practice for this repository structure.
Audit Metadata