aws-cost-cleanup

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides numerous scripts and commands that execute high-privilege AWS operations.
  • Evidence: Scripts use aws ec2 delete-volume, aws ec2 delete-snapshot, and aws ec2 release-address to modify the cloud environment.
  • Evidence: Python scripts utilize the boto3 library to programmatically delete resources through the ec2.delete_volume method.
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection (Category 8).
  • Ingestion points: The skill reads metadata from AWS resources, such as volume IDs, snapshot start times, and potentially resource tags during discovery phases (e.g., calculate-savings.py and lambda_handler).
  • Boundary markers: None identified in the provided scripts or prompt examples.
  • Capability inventory: High-impact capabilities include subprocess execution of AWS CLI commands and Python-based resource deletion.
  • Sanitization: No explicit sanitization or filtering of external resource metadata is performed before the data is processed or displayed.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 07:42 PM