The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using helm and kubectl to deploy and manage application resources on a Kubernetes cluster. This includes common deployment operations such as helm upgrade --install, helm dependency build, and kubectl rollout status. It also uses curl to verify application readiness via health endpoints.\n- [EXTERNAL_DOWNLOADS]: The skill fetches Helm charts and dependencies from an external registry. Specifically, it uses helm pull to download the chat-question-and-answer-core chart from the official Intel repository on Docker Hub (oci://registry-1.docker.io/intel/). This is a standard procedure for retrieving verified deployment artifacts from a well-known vendor.\n- [PROMPT_INJECTION]: The skill features a surface for indirect prompt injection as it incorporates user-supplied configuration variables and environment parameters directly into shell command arguments and generated YAML files.\n
Ingestion points: Data enters the execution flow via user-specified parameters such as target namespace, release name, and version tags (e.g., BACKEND_TAG, UI_TAG) provided through prompts or environment variable mappings.\n
Boundary markers: There are no explicit delimiters or instructions provided to isolate or escape user-controlled data within the shell commands.\n
Capability inventory: The skill leverages high-privilege tools such as helm and kubectl to modify cluster state and curl to interact with the network.\n
Sanitization: The instructions do not define validation or sanitization routines for input strings before they are interpolated into executable shell commands.

chatqna-helm-deploy