aws-cli
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references the official
aws-actions/configure-aws-credentialsGitHub Action in its CI/CD examples for secure OIDC authentication. - [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process external data from AWS CLI command outputs (JSON/Text) to perform operations.
- Ingestion points: Command outputs from
aws sts get-caller-identity,aws configure list, and service-specific describe/list calls. - Boundary markers: None explicitly defined in the provided markdown, but the skill mandates identity verification steps.
- Capability inventory: Subprocess execution of AWS CLI commands for resource management, including deletion and termination of cloud resources.
- Sanitization: The skill explicitly instructs agents to redact secret keys and session tokens in output and chat logs.
Audit Metadata