k8s
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches Kubernetes manifests from official repositories of cert-manager and rancher on GitHub.
- [REMOTE_CODE_EXECUTION]: Includes an optional prerequisite step to install Helm using a script downloaded from the official Helm project and executed via bash.
- [COMMAND_EXECUTION]: Instructs the agent to perform deployment operations in an autopilot mode, managing file creation and cluster commands autonomously.
- [DYNAMIC_EXECUTION]: Generates configuration files and a shell script for secret management at runtime using user-provided parameters.
- [INDIRECT_PROMPT_INJECTION]: 1. Ingestion points: User provides setup data like domain names, email addresses, and license keys. 2. Boundary markers: No specific delimiters are used for user-supplied values. 3. Capability inventory: The skill utilizes subprocess execution for kubectl, helm, and shell commands. 4. Sanitization: No explicit sanitization or validation of user-provided strings is performed before interpolation into commands.
Audit Metadata