agents-deploy

Pass

Audited by Gen Agent Trust Hub on May 7, 2026

Risk Level: SAFE
Full Analysis
  • Standard Command Execution: The skill utilizes bash to execute AWS CLI commands (aws sts, aws bedrock, aws iam) and the agentcore CLI. These operations are used to verify credentials, check model access, and perform deployments, which aligns with the skill's primary purpose.
  • Access to Configuration Files: The skill reads local files such as agentcore/agentcore.json and agentcore/aws-targets.json. This is a necessary step for pre-flight validation and environment targeting during the deployment process.
  • Indirect Prompt Injection Surface: The skill processes information from deployment logs and configuration files. While these are ingestion points for external data, the skill uses them strictly for diagnostic output and status checks, which is standard behavior for troubleshooting tools.
  • Trusted Infrastructure Interaction: Deployment operations and model access checks target well-known AWS services. The use of npx cdk bootstrap is a routine administrative task for setting up AWS Cloud Development Kit environments.
Audit Metadata
Risk Level
SAFE
Analyzed
May 7, 2026, 07:15 PM