iam
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill documents administrative commands for managing AWS identities, such as
aws iam create-role,aws iam attach-role-policy, andaws sts assume-role. These capabilities are standard for IAM administration and are aligned with the skill's stated purpose for managing access control. - [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for fetching data from AWS services, which creates a potential surface for processing untrusted data (such as CloudTrail events or credential reports) that could theoretically contain injection payloads from actors with access to the environment.
- Ingestion points:
best-practices.md(reading events viaaws cloudtrail lookup-eventsand reports viaaws iam get-credential-report). - Boundary markers: Not present in the provided command examples.
- Capability inventory: Extensive IAM management operations across the AWS CLI suite and Boto3 library.
- Sanitization: None; the skill assumes the integrity of standard AWS service responses.
Audit Metadata