k8s-helm

Fail

Audited by Gen Agent Trust Hub on Nov 9, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches the official Helm installation script from the project's public GitHub repository.
  • [REMOTE_CODE_EXECUTION]: Executes the Helm installation script via a shell pipe to verify prerequisites.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes Helm charts and template files which may contain untrusted data.
  • Ingestion points: Chart paths and values provided to tools in SKILL.md and processed by scripts/lint-chart.sh.
  • Capability inventory: Subprocess execution of helm and kubectl commands across various tools including installation and package management.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded instructions are present in the documentation.
  • Sanitization: Relies on the Helm CLI's internal parsing and validation mechanisms.
Recommendations
  • HIGH: Downloads and executes remote code from: https://raw.githubusercontent.com/helm/helm/main/scripts/get-helm-3 - DO NOT USE without thorough review
Audit Metadata
Risk Level
HIGH
Analyzed
Nov 9, 2026, 06:52 PM