The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use standard command-line utilities such as kubectl, docker, grep, and cluster-specific tools like kind or minikube. These tools are used for environment discovery, building and loading images, and managing the lifecycle of Kubernetes deployments.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from external files and cluster state, which represents a potential injection surface.
Ingestion points: Dependency manifest files (requirements.txt, package.json, Gemfile, go.mod, pom.xml) and Kubernetes resource specifications retrieved via kubectl.
Boundary markers: No specific boundary markers or instructions are provided to the agent to treat this ingested data as potentially untrusted.
Capability inventory: The skill possesses the ability to execute shell commands, perform container builds, and modify Kubernetes resources.
Sanitization: No explicit sanitization or validation steps are defined for the data extracted from the environment before it is used in subsequent operations.

enable-ssi