The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides instructions for executing shell commands to manage Kubernetes resources. Evidence: Commands such as helm install, helm upgrade, and kubectl diff are explicitly documented in SKILL.md.
[INDIRECT_PROMPT_INJECTION]: The skill utilizes a templating mechanism where external configuration values are interpolated into Kubernetes manifests. 1. Ingestion points: Untrusted data is ingested through values.yaml and command-line --set flags in SKILL.md. 2. Boundary markers: The templates lack explicit delimiters or instructions to ignore embedded commands within variable values. 3. Capability inventory: The skill uses helm and kubectl in SKILL.md to deploy resources, providing a path from data ingestion to environment modification. 4. Sanitization: Manifest generation relies on standard Helm functions without additional security-focused sanitization of user-provided values.
[EXTERNAL_DOWNLOADS]: The skill includes instructions for fetching third-party application charts from external sources. Evidence: The skill fetches configuration and packages from the Bitnami repository (https://charts.bitnami.com/bitnami), which is a well-known service for containerized applications.

helm-charts