helm-expert

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches Helm charts and updates from well-known repositories including Bitnami (charts.bitnami.com) and the official Helm Stable repository (charts.helm.sh).
  • [COMMAND_EXECUTION]: Executes shell commands via Bash for Helm and Kubectl operations, including chart creation, installation, linting, and deployment management.
  • [INDIRECT_PROMPT_INJECTION]: The skill functions by processing external infrastructure configuration data.
  • Ingestion points: The skill instructions involve reading and processing local Helm chart directories and YAML configuration files (e.g., values.yaml) supplied by the user.
  • Boundary markers: There are no explicit delimiters or instructions for the agent to disregard natural language directives that might be embedded within chart comments or templates.
  • Capability inventory: The agent possesses file system modification rights (Write, Edit) and administrative shell access restricted to helm and kubectl binaries.
  • Sanitization: The workflow relies on standard Helm validation tools (helm lint, helm template) but does not include additional sanitization for malicious content embedded in templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 06:42 PM
Security Audit — agent-trust-hub — helm-expert