Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
Add output DLP, escalation, and behavioral monitoring (v0.2.0)
What This Skill Does
Deny-by-default governance layer for OpenClaw that intercepts every tool call before execution. Runs five mandatory checks: identity verification, scope enforcement, rate limiting, prompt injection detection, and audit logging. Three optional features add output DLP, human escalation, and behavioral monitoring.
Because it hooks at the process level, the agent cannot route around it the way it could with in-prompt or middleware-based guardrails.
When to use it
- Blocking an agent from calling tools outside its approved scope
- Detecting prompt injection attempts before a tool executes
- Reviewing audit logs after an unexpected agent action
- Redacting PII from tool output before it reaches the agent
- Triggering human review when an agent tries a tool for the first time
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: why did the agent get blocked from calling the file_write tool?
- 1Check append-only audit log at ~/.openclaw/plugins/gatewaystack-governance/audit.jsonl
- 2Locate the denial record for the file_write invocation
- 3Read the policy role assigned to the agent under the identity check
- 4Confirm file_write is absent from the agent's tool allowlist in policy.json
- 5Return the denial reason and the policy entry that caused it
Audit entry showing file_write was denied because the agent's policy role does not include it in the scope allowlist
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.