Verticals / OpenClaw

Every AI skill
must be governed.

Before installation. During execution.

OpenClaw scans AI skill packages through five governance gates, signs the verdict, and anchors it in a transparency log — producing cryptographic proof that the skill was safe to run.

01 — The Problem

Package managers install.

OpenClaw governs.

AI skill packages execute with the same authority as the host agent. A compromised skill can exfiltrate data, manipulate outputs, or override safety controls.

OpenClaw evaluates every skill before execution. If a skill fails any gate, it does not run.

02 — The Five Gates

Scan. Gate.
Prove.

G1

Statistical Confidence

Measures whether the skill's declared capabilities are statistically supported by its test evidence.

Observable: entropy (H) ≥ 0.40
G2

Causal Attribution

Verifies that skill outputs can be causally attributed to its declared inputs — not side effects.

Observable: coherence (C) ≥ 0.40
G3

Regression Safety

Ensures the skill does not degrade the host system's operational safety below acceptable bounds.

Observable: energy (E) ≤ 0.60
G4

Evidence Integrity

Validates the cryptographic integrity of all evidence submitted with the skill package.

PASS ADMIT
REVIEW QUARANTINE
BLOCK REFUSE
G5

Human Authorization

Requires explicit human consent before any skill with elevated permissions is admitted. Signs the decision and anchors it in the transparency log.

03 — Two Products

Self-hosted.
Or managed.

Self-Hosted

ClawGuard

Install as an npm package in your ClawHub environment. Skills are scanned locally through the five-gate protocol, with governance verdicts anchored in the ObligationSign transparency log.

npm install @openclaw/clawguard
Token-issuing registration
Transparent degraded mode (no auth)
Key Registry revocation
Free tier: 50 scans/month. Pro: 500/month. Enterprise: unlimited.
Managed

OpenClaw Starter

A fully managed Cloudflare-native environment. No local installation — scan skills via API or the web dashboard. Governance infrastructure is operated by ObligationSign.

Web dashboard with live gate verdicts
REST API + MCP SSE integration
Community trust scoring
Proof chain verification portal
Same governance protocol. Zero infrastructure to manage.

Both products use the same AGTS five-gate protocol and the same transparency log.

Feature Comparison

Feature ClawGuard OpenClaw Starter
Deployment Self-hosted (npm) Managed (Cloudflare edge)
Five-Gate Protocol G1–G5 G1–G5
Transparency Log AGTS anchored AGTS anchored
LLM Inference BYO (local) 3-tier: Workers AI / BYOK / Managed
Agent Management Full lifecycle (create/start/stop/checkpoint)
Chat / WebSocket Real-time streaming + governance
BYOK Vault AES-GCM encrypted KV
File Storage R2-backed per agent
Web Dashboard Full dashboard + chat UI
API Keys Token-based registration Scoped per-agent keys
Free Tier 50 scans/month 500 events/month
Infrastructure You manage Zero — fully managed

04 — Why Governance, Not Detection

Valid Package.
Valid Signature.
Malicious Behavior.

Invisible to Package Managers

Skills that pass type checks but exfiltrate context data through side channels

Invisible to Package Managers

Skills that override safety controls through prompt injection vectors

Invisible to Package Managers

Skills with valid signatures but statistically unsupported capability claims

These pass npm install.

They do not pass OpenClaw.

05 — Proof, Not Trust

Every governance decision is independently verifiable.

The scan result, gate verdicts, and cryptographic proof are anchored in the same AGTS transparency log used by every ObligationSign vertical. Anyone can verify that a skill was admitted — or refused — without trusting the scanner.

Verification Flow
1. Scan skill.json → five-gate evaluation
2. Sign verdict with Ed25519
3. Anchor leaf in transparency log
4. Return leaf hash + inclusion proof
5. Anyone verifies at /verify/openclaw/
API
POST /v1/openclaw/scan
GET /v1/openclaw/quota
POST /v1/openclaw/register
POST /v1/openclaw/govern
MCP SSE: agts.obligationsign.com/mcp/sse

06 — Start Governing

Choose your deployment model.