Openclaw Shield
A Claude skill from davidtoby/agent-skills.
Install
$ agentstack add skill-davidtoby-agent-skills-openclaw-shield ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-davidtoby-agent-skills-openclaw-shield) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
OpenClaw Shield
Enterprise security scanner for AI agents. Detects credential theft, data exfiltration, and malicious code with static analysis + runtime guards + ClamAV integration. Audit logging and tamper-evident reports.
When to use: Security scanning, threat detection, code auditing, runtime protection for AI agents
What to know:
Repository: https://github.com/pfaria32/OpenClaw-Shield-Security
Features
Static Scanner
- Detects credential theft, data exfiltration, destructive operations
- Pattern-based analysis (no external dependencies)
- Python stdlib only (zero supply chain risk)
- Pre-execution scanning
Runtime Guard
- File/network/exec allowlists
- Output sanitization
- Policy enforcement
- Real-time protection
Integration
- ClamAV integration (3.6M virus signatures)
- Telegram alerting on critical findings
- Hash-chained audit logging
- Tamper-evident security logs
Installation
cd /home/node/.openclaw/workspace
git clone https://github.com/pfaria32/OpenClaw-Shield-Security.git projects/OpenClaw-Shield
# Test the scanner
python3 projects/OpenClaw-Shield/src/scanner.py /path/to/scan
# Deploy (see repository README for full setup)Usage
Manual Scan
python3 projects/OpenClaw-Shield/src/scanner.py workspace --output shield-report.jsonDaily Automated Scans
Set up cron job (see repository deployment guide):
# Daily at 3 AM UTC
0 3 * * * /path/to/scan-script.shRuntime Guard (Optional)
Configure allowlists and enable runtime protection (see deployment/openclaw-config.py in repo).
Status
✅ Deployed on this instance (clawdbot-toronto)
- Daily scans: 3:00 AM UTC
- ClamAV: Active (host-level)
- Runtime guard: Prepared (not enabled by default)
Attribution
Inspired by: Resonant by Manolo Remiddi Source: https://github.com/ManoloRemiddi/resonantos-open-system-toolkit/blob/main/BUILDYOUROWN_SHIELD.md
Built on the principle: "Don't trust, verify."
Documentation
Full docs, threat model, and deployment guide in repository README.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: davidtoby
- Source: davidtoby/agent-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.