infra-bootstrap
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to execute infrastructure commands through a local script located at
./scripts/agents/tooling/agentTool.ts. This capability is limited to a predefined allowlist of stacks (staging/k8s, prod/k8s, prod/vpn) and specific actions (apply, apply01, apply02, apply03, destroy). Safety constraints are implemented to ensure user confirmation and proper error handling.
Audit Metadata