aws-iam
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides numerous AWS CLI commands for managing identity resources. These include creating roles (
aws iam create-role), attaching policies (aws iam attach-role-policy), and managing instance profiles. - [DATA_EXPOSURE]: Includes instructions for generating and downloading AWS credential reports (
aws iam generate-credential-report). While these reports contain sensitive metadata about account security status, the functionality is a standard part of AWS security auditing and is consistent with the skill's stated purpose. - [INDIRECT_PROMPT_INJECTION]: The skill defines patterns for ingesting local policy files (e.g.,
file://trust-policy.json) and processing repository identifiers in OIDC trust relationships. - Ingestion points: Command line arguments and local file references (
SKILL.md). - Boundary markers: None explicitly defined in the provided commands, though standard AWS JSON syntax is used.
- Capability inventory: Significant capability to mutate AWS IAM state via subprocess calls to the AWS CLI.
- Sanitization: Relies on AWS CLI and API validation of the provided JSON documents.
Audit Metadata