The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided AWS configuration data and infrastructure requirements to generate CLI commands and deployment manifests. This creates an attack surface where malicious instructions embedded in user-supplied data could influence agent behavior.
Ingestion points: User queries regarding EKS/ECS/ECR setups and existing configuration files provided for debugging or optimization.
Boundary markers: Not present. The skill does not specify delimiters or instructions to ignore embedded commands in the data it processes.
Capability inventory: As stated in SKILL.md, the skill is intended to work with an AWS MCP server which provides capabilities for executing shell commands and AWS API calls.
Sanitization: Not present. There are no explicit instructions to sanitize or validate user input before it is used to generate executable commands.
[EXTERNAL_DOWNLOADS]: The skill provides instructions for downloading IAM policies and Helm charts from external repositories.
Evidence: References to https://raw.githubusercontent.com/kubernetes-sigs/aws-load-balancer-controller and https://aws.github.io/eks-charts for downloading operational configuration and deploying controllers. These sources are well-known community and vendor repositories associated with the skill's primary purpose.

aws-containers