The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes a bash script scripts/validate-chart.sh designed to automate the validation of Helm charts by executing local CLI tools including helm, grep, awk, and jq.
[EXTERNAL_DOWNLOADS]: The skill configuration templates and instructions reference external Helm chart repositories, notably from Bitnami (https://charts.bitnami.com/bitnami), to facilitate dependency management via standard Helm commands.
[CREDENTIALS_UNSAFE]: The assets/values.yaml.template file and example code in SKILL.md contain a hardcoded default password (password: changeme) for a database dependency. While intended as a placeholder, providing default credentials in configuration templates is a weak security practice.
[INDIRECT_PROMPT_INJECTION]: The validation script provided with the skill ingests external Helm chart data, creating a surface for indirect prompt injection.
Ingestion points: The script scripts/validate-chart.sh processes files from a user-supplied directory (CHART_DIR).
Boundary markers: Absent; the script does not implement specific delimiters or instructions to ignore potentially malicious content embedded in chart metadata or templates.
Capability inventory: The script utilizes the helm CLI to lint and render templates, which involves full execution of the Go template engine on the ingested data.
Sanitization: Absent; the script performs basic checks using grep and awk but does not sanitize or escape the content before passing it to the Helm engine.

helm-chart-scaffolding