database-cloud-optimization-cost-optimize
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill contains Python scripts and Terraform configurations in
resources/implementation-playbook.mdthat utilizeboto3to perform active operations on cloud infrastructure, includingstop_instances,modify_instance_attribute, andput_bucket_lifecycle_configuration. While intended for optimization, these represent high-privilege capabilities. - [INDIRECT_PROMPT_INJECTION]: The skill has a defined attack surface for indirect prompt injection:
- Ingestion points: The skill reads data from AWS CloudWatch, Cost Explorer, and Resource APIs (e.g.,
ec2.describe_instances,s3.list_buckets) into the agent context viaresources/implementation-playbook.md. - Boundary markers: The instructions lack explicit boundary markers or instructions for the agent to ignore embedded commands within the resource metadata it analyzes.
- Capability inventory: The scripts include capabilities to modify instance types, stop instances, and update S3 policies (
resources/implementation-playbook.md). - Sanitization: There is no evidence of sanitization for resource tags or metadata retrieved from the cloud provider before being processed by the logic.
Audit Metadata