The Agent Skills Directory

[COMMAND_EXECUTION]: The skill guides the agent to execute task renovate:validate. This is a standard command used to verify the syntax and correctness of Renovate configuration files and is consistent with the skill's stated administrative purpose.
[PROMPT_INJECTION]: The skill's workflow involves processing external data, which introduces an indirect prompt injection surface.
Ingestion points: The agent is instructed to read and modify kubernetes/platform/versions.env, .github/renovate.json5, and Kubernetes YAML manifests.
Boundary markers: The instructions do not define specific delimiters or guardrails to prevent the agent from following instructions potentially embedded in these configuration files.
Capability inventory: The agent has the capability to perform file I/O operations and execute shell commands via the task runner.
Sanitization: No explicit validation or sanitization routines are provided for the content read from the external configuration files.
[NO_CODE]: The skill consists exclusively of markdown documentation and YAML metadata. It does not include any executable scripts, binaries, or automated code blocks.
[SAFE]: All external references, such as those for Helm charts and container images, point to well-known and reputable services including GitHub and the GitHub Container Registry (GHCR).

versions-renovate