aws-account-cleanup

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the AWS CLI to perform inventory and resource deletion across multiple services (EC2, S3, RDS, IAM, etc.). This behavior is consistent with the skill's stated purpose of account cleanup.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the AWS environment, such as resource names and tags.
  • Ingestion points: Metadata retrieved via AWS CLI commands (e.g., describe-instances, list-buckets).
  • Boundary markers: The skill mandates the use of specific, unambiguous confirmation strings like please confirm delete xxx from your xxx account to prevent automated or accidental execution.
  • Capability inventory: Extensive deletion and modification capabilities across a wide range of AWS services via the aws tool.
  • Sanitization: The skill relies on a human-in-the-loop workflow where a dry-run summary is presented for manual review and approval before any deletion commands are executed.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 11:55 AM
Security Audit — agent-trust-hub — aws-account-cleanup