A comprehensive security audit and threat modeling tool designed to verify the integrity and safety of OpenClaw gateway hosts.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install clawdstrike
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install clawdstrike using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is ClawdStrike?
ClawdStrike is a specialized security auditing skill for OpenClaw environments. It focuses on identifying misconfigurations, real-world attack paths, and filesystem hygiene issues to ensure your Openclaw Skills operate in a secure environment. The tool operates in a strict Verified mode to prevent unauthorized command execution while generating detailed OK/VULNERABLE reports.
By analyzing gateway exposure, plugin inventory, and network configurations, ClawdStrike provides developers and system administrators with the evidence-based insights needed to harden their AI agent infrastructure. It prioritizes safety by redacting sensitive data and requiring explicit consent for any system changes or fixes.
ClawdStrike Use Cases
- Auditing an OpenClaw deployment for potential security vulnerabilities.
- Verifying filesystem permissions and hygiene for gateway hosts.
- Scanning third-party Openclaw Skills for suspicious patterns or unauthorized instructions.
- Generating deterministic security reports for compliance or operational oversight.
- Threat modeling specific gateway configurations to identify exposure risks.
How ClawdStrike Works
- Initialize security collection by executing the verified collection script to gather system state.
- Analyze the generated data bundle against a mandatory checklist of security requirements.
- Evaluate network exposure, firewall status, and discovery protocols like mDNS.
- Inventory all installed plugins and skills to detect supply chain risks.
- Generate a comprehensive report featuring a findings table, threat model, and suggested remediation steps.
ClawdStrike Setup
To begin auditing your Openclaw Skills environment, ensure you are in the project root and run the following command:
# Run the standard verified collection script
scripts/collect_verified.sh
# For a deeper probe of the local gateway host (requires explicit request)
scripts/collect_verified.sh --deep
After execution, the skill will consume the verified-bundle.json to produce the audit report.
ClawdStrike Data Schema & Taxonomy
ClawdStrike organizes its findings based on structured reference data and evidence collected from the host system.
| Component | Source File/Key | Description |
|---|---|---|
| Audit Results | verified-bundle.json | The primary source of system state and evidence. |
| Check Definitions | references/required-checks.md | The logic used to determine OK vs VULNERABLE status. |
| Evidence Logs | references/evidence-template.md | Defines how evidence is formatted and redacted. |
| Security Policies | references/verified-allowlist.md | The strict set of commands allowed during the audit. |
ClawdStrike Advanced Features
- Deep local gateway probing for exhaustive security analysis.
- Automated redaction of tokens, passwords, and OAuth credentials to prevent secret exfiltration.
- Supply chain scanning to identify patterns in third-party Openclaw Skills.
- Strict Verified-mode execution ensuring no unauthorized remote content is processed.
- Customizable fix instructions that empower users to harden their systems manually.
SKILL.md
Loading
Related Openclaw Skills
Clawstrike Security Audit
A specialized security auditing tool that produces deterministic vulnerability reports and threat models for Openclaw gateway environments.
Lore Knowledge Base
A sophisticated research repository skill that enables AI agents to ingest, search, and synthesize knowledge with full source citations.
Hot Dog or Not — Battle Skill
A competitive food classification skill that pits your AI agent against NVIDIA's Nemotron model to determine if a photo contains a hot dog.
Space Jobs
Search and apply for thousands of space industry jobs across top aerospace companies directly through your AI agent.
Clawstrike Security Audit
A comprehensive security auditing tool designed to identify misconfigurations and attack paths within OpenClaw deployments.
OpenClaw Security Audit
A read-only security auditor designed to identify misconfigurations, credential leakage, and attack vectors in OpenClaw and Clawdbot deployments.
METADATA
Featured*
