aws-infra
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides comprehensive instructions for managing AWS infrastructure using standard tooling including the AWS CLI and the
boto3Python library. - The provided snippets allow the agent to perform administrative tasks such as listing resources, deploying CloudFormation stacks, managing EKS clusters, and invoking Lambda functions.
- While these are high-privilege operations, they are explicitly aligned with the skill's stated purpose of AWS infrastructure management.
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface: The skill interacts with external data (AWS resource metadata, stack events, and logs) which constitutes an ingestion point for potentially untrusted data.
- Ingestion points:
list_resources,describe_stacks,describe_stack_events,list_functionsinSKILL.md. - Boundary markers: No explicit boundary markers or 'ignore' instructions are used when processing resource data.
- Capability inventory: The skill has the capability to create resources (
create_resource), invoke code (invoke), and update local configuration (update-kubeconfig). - Sanitization: No input sanitization or validation of the ingested AWS metadata is present in the provided templates.
- Note: This represents a standard attack surface for infrastructure management tools rather than a malicious implementation.
Audit Metadata