aws-account-management
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes numerous AWS CLI commands for administrative and auditing tasks. This includes the command
aws iam get-credential-report --output text --query Content | base64 -d, which decodes and displays an account-wide credential audit report containing metadata about user access and MFA status. - [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection due to its interaction with external cloud data.
- Ingestion points: Data is ingested from AWS APIs through commands such as
aws iam list-usersand via Python'sboto3client inSKILL.md. - Boundary markers: The skill does not implement boundary markers or instructions for the agent to ignore potentially malicious content embedded in AWS resource metadata.
- Capability inventory: The skill possesses high-privilege capabilities including organization management (
aws organizations create-account), identity management (aws sso-admin create-permission-set), and policy configuration. - Sanitization: There is no evidence of data sanitization or validation performed on the retrieved AWS identifiers or report data before it is processed by the agent.
Audit Metadata