amazon-braket
Pass
Audited by Gen Agent Trust Hub on Aug 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- Command Execution: The skill instructs the agent to use local shell tools and Python execution to interact with the Amazon Braket SDK and AWS CLI. This is a standard method for performing administrative tasks, managing quantum circuits, and querying device status within a developer environment.
- External Resource Access: The skill references official AWS documentation, SDK documentation on ReadTheDocs, and source code from the Amazon Braket GitHub organization. These resources are utilized to verify API signatures, pricing, and device capabilities, which helps ensure the agent operates with the most current and accurate information.
- Data Ingestion Surface: The skill processes device metadata and capability strings (JSON-encoded) returned by AWS APIs. While this constitutes a surface for processing external data, the instructions emphasize using structured tools like
jqand specific SDK properties to extract fields, which helps mitigate risks associated with unstructured data processing. - Security Best Practices: The documentation includes extensive guidance on least-privilege IAM policies, CloudTrail auditing, and the proper use of AWS Secrets Manager for handling credentials within hybrid jobs, promoting a secure operational posture.
Audit Metadata