governance-guard

Governance guard enforces structural authority separation on all agent actions through a PROPOSE-DECIDE-PROMOTE pipeline.

When to activate

Before performing any write, execute, network, create, or delete action. The governance pipeline MUST be invoked before the action executes. Read actions may also be governed under standard or strict policies.

How to use

1. Full pipeline (recommended)

Run the complete PROPOSE → DECIDE → PROMOTE pipeline in a single call:

CODEBLOCK0

The intent JSON must include:

• - skill: skill identifier
• INLINECODE1: tool/function being invoked
• INLINECODE2: LLM model name
• INLINECODE3: one of read, write, execute, network, create, INLINECODE9
• INLINECODE10: resource being acted upon
• INLINECODE11: tool parameters (object)
• INLINECODE12: data categories accessed (array, e.g. ["personal", "financial"])
• INLINECODE14: current conversation ID
• INLINECODE15: current message ID
• INLINECODE16: the user message that triggered this action

2. Handle the verdict

The pipeline returns a JSON response:

• - If "governance": "approved" — proceed with the action
• If "governance": "deny" — do NOT proceed; inform the user with the INLINECODE19
• If "governance": "escalate" — present the action to the user for approval:

CODEBLOCK1

Then resolve:

CODEBLOCK2

3. Audit decisions

CODEBLOCK3

Policy presets

Fail-closed guarantee

If any error occurs during governance evaluation, the default verdict is DENY. Missing policy files result in DENY ALL. This is by design. The system fails safe, never open.

Configuration

Governance data is stored in ~/.openclaw/governance/:

• - policy.yaml — active policy file
• INLINECODE26 — append-only, hash-chained audit log

Verify witness chain

CODEBLOCK4

Any tampering with historical records is detected by recomputing the hash chain from genesis.