The Agent Skills Directory

[SAFE]: The skill follows security best practices by explicitly instructing the user to use the --context flag in commands to prevent accidental operations on incorrect clusters. All listed tools and commands are standard for the described purpose.
[PROMPT_INJECTION]: The skill processes potentially untrusted content from Helm charts and values files as part of its core debugging functionality. While this presents a surface for indirect prompt injection, it is necessary for the skill's primary objective.
Ingestion points: Reads Helm chart templates, local files, and values files using helm lint, helm template, and helm install (SKILL.md, REFERENCE.md).
Boundary markers: None explicitly present to separate processed data from instructions.
Capability inventory: Executes shell commands including helm and kubectl via the Bash tool.
Sanitization: No specific validation or escaping of chart content is documented.

helm-debugging