amazon-transcribe
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill exclusively references official Amazon Web Services (AWS) documentation and domains (aws.amazon.com, amazon.com), which are well-known and trusted services. These references are used appropriately for providing technical context.
- [SAFE]: Python code examples utilize the standard
boto3library for AWS interactions. The code follows security best practices by not hardcoding credentials and instead relying on default client initialization, which typically uses environment variables or IAM roles. - [SAFE]: The skill provides explicit security and privacy guidance, including instructions for PII/PHI redaction, AWS KMS encryption at rest, and opting out of AI service content improvement programs. It correctly identifies the 'Shared Responsibility Model'.
- [SAFE]: Instructions regarding Amazon Transcribe Medical and Call Analytics emphasize the critical need for human review in sensitive workflows, preventing over-reliance on automated AI outputs for patient care or legal compliance.
Audit Metadata