Helm Chart Auditor
Analysis
This is a coherent, instruction-only Helm chart review skill; its file reads and linting commands match the audit purpose, though users should avoid exposing real secrets in chart values.
Findings (3)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
cat Chart.yaml 2>/dev/null cat values.yaml 2>/dev/null | head -50 ls templates/ 2>/dev/null helm lint . 2>&1
The skill instructs the agent to read local Helm chart files and run Helm linting. These actions are purpose-aligned and scoped, but users should notice that the skill can inspect local project contents.
Required binaries (all must exist): none
The SKILL.md workflow references `helm lint`, but the registry requirements do not declare Helm as a required binary. This is a minor setup metadata gap rather than hidden code or an unsafe installer.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
cat values.yaml 2>/dev/null | head -50
values.yaml can contain secrets or environment-specific configuration. Inspecting it is expected for a Helm security audit, but it may place sensitive chart data into the agent's working context.