The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Fetches Kubernetes security auditing manifests from Aqua Security's official GitHub repository for CIS benchmarking.
[EXTERNAL_DOWNLOADS]: References the official Aqua Security container image for running security scans.
[COMMAND_EXECUTION]: Executes multiple kubectl and jq commands to inspect cluster configuration, audit RBAC permissions, and check for security policy violations.
[PROMPT_INJECTION]: Presents a surface for indirect prompt injection through the processing of cluster data.
Ingestion points: The skill uses kubectl get commands in SKILL.md to retrieve cluster resource definitions (Pods, RoleBindings, etc.) in JSON format for analysis.
Boundary markers: The provided command patterns do not include specific delimiters or instructions to the agent to ignore potentially malicious content embedded within the retrieved resource data.
Capability inventory: The skill includes the mcp__flux-operator-mcp__apply_kubernetes_manifest tool, allowing it to modify the cluster state based on its analysis.
Sanitization: There is no explicit mention of sanitizing or validating the content of the Kubernetes resources before the agent processes them.

k8s-security-hardening