The Agent Skills Directory

[COMMAND_EXECUTION]: The skill orchestrates deployments by executing standard CLI utilities including helm, kubectl, git, gh, task, and hubble. All commands are used within the scope of application management.\n- [EXTERNAL_DOWNLOADS]: Fetches Helm charts and metadata from well-known registries such as Artifact Hub and GHCR. These downloads are required for the installation of Kubernetes applications and originate from trusted or well-known services.\n- [DATA_EXFILTRATION]: Accesses the local Kubernetes configuration file located at ~/.kube/dev.yaml to authenticate with clusters. This access is necessary for the skill's deployment and validation functions and is not used for external exfiltration.\n- [PROMPT_INJECTION]: Vulnerable to indirect prompt injection through the processing of untrusted external data. Ingestion points: Reads application logs via kubectl logs and Helm chart metadata from external search results. Boundary markers: None; the skill does not use specific delimiters to isolate external content. Capability inventory: Includes broad capabilities for file modification and command execution. Sanitization: No explicit sanitization of log or search content is performed before presentation to the agent.

deploy-app