helm-chart-development

Warn

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill facilitates the use of helm and kubectl commands to manage Kubernetes cluster resources, allowing for the installation and testing of applications.
  • [DATA_EXFILTRATION]: The skill references the sensitive path ~/.gnupg/secring.gpg for chart signing operations. Accessing private GPG keyrings is a high-risk activity that could lead to credential exposure.
  • [EXTERNAL_DOWNLOADS]: The skill performs network operations via helm dependency update to fetch charts from external repositories such as Bitnami and OCI registries. These are standard developer tasks but involve external network interaction.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection by processing Helm chart templates and values from the local environment without sanitization.
  • Ingestion points: helm lint, helm template, and helm install read data from ./mychart.
  • Boundary markers: No explicit markers are defined to isolate untrusted chart content from the agent's instructions.
  • Capability inventory: The agent can execute bash commands and perform file system operations.
  • Sanitization: The skill lacks validation steps for chart content before processing.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 27, 2026, 07:13 PM