openclaw-hardening
Skill0 starsChanged 10 months agoMITView on GitHub
A comprehensive security auditor for OpenClaw/Moltbot/Clawdbot instances. It checks for common misconfigurations, insecure network bindings, and exposed secrets. Use this skill when a user asks to "secure my agent," "audit openclaw," "check for vulnerabilities," or "harden my configuration.
- Reads credentials
2 other projects use a version of this.
Adopted by
Most recently taken up by
- billyhetech/clawshelf-skillstheir own version, first seen Oct 25, 2026
- nradawg/openclaw-hardeningtheir own version, first seen Jun 12, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- billyhetech/clawshelf-skills★ 0same name
- nradawg/openclaw-hardening★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repositoryOne other file it gives its agents.
- superset-apiSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 1 is distinctive, and 6 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 15
Search for the primary configuration file.
- Distinctive: line 17
Check Network Bindings (CRITICAL):
- Very specific: line 25
Check for gateway.auth.token or gateway.auth.password.
- Very specific: line 45
Verify permissions of the .openclaw directory.
- Very specific: line 46
Verify permissions of openclaw.json.
- Very specific: line 76
When executing shell commands to check permissions (e.g., ls -l), use the bash tool.
- Very specific: line 77
When reading config files, use the fs.readFile tool.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
OpenClaw Hardening & Security Auditor
This skill provides a structured workflow to analyze the security posture of an OpenClaw deployment. It focuses on identifying the "Lethal Trifecta" of risks: Privileged Access, Network Exposure, and Untrusted Input.
Instructions
Phase 1: Reconnaissance & Configuration Analysis
- Locate Configuration:
- Search for the primary configuration file. Check standard locations in order:
~/.openclaw/openclaw.json,~/.moltbot/config.json, or the directory specified in theOPENCLAW_CONFIGenvironment variable. - Load the file and identify the
gatewayconfiguration block.
- Search for the primary configuration file. Check standard locations in order:
- Check Network Bindings (CRITICAL):
- Inspect
gateway.bind.- PASS: If set to
"loopback"or127.0.0.1. - FAIL: If set to
"0.0.0.0","lan", or a public IP address.
- PASS: If set to
- Inspect
gateway.port. Note the port (default18789). - Proxy Vulnerability Check: Check if the environment suggests a reverse proxy usage (e.g., presence of Nginx/Caddy config files). If a proxy is likely, verify if
gateway.trustedProxiesis configured inopenclaw.json.- RISK: If
trustedProxiesis missing or empty, flag as HIGH RISK (Localhost Trust Bypass Vulnerability).
- RISK: If
- Inspect
- Authentication Verification:
- Check for
gateway.auth.tokenorgateway.auth.password. - FAIL: If these are null, empty, or set to default strings (e.g., "changeme", "password").
- CRITICAL: Check for dangerous flags:
gateway.controlUi.allowInsecureAuthordangerouslyDisableDeviceAuth. If either istrue, flag as CRITICAL.
- Check for
- Sandbox Status:
- Inspect
agents.defaults.sandbox. - PASS: If
modeis"non-main"or"all". - WARN: If
modeis"off". - FAIL: If the process is running as
rootuser without strict sandboxing.
- Inspect
Phase 2: Skill Auditing
- Review Installed Skills:
- List contents of
~/.openclaw/skills/or~/.openclaw/extensions/. - Malware Scan: Search skill directories for suspicious keywords in
manifest.jsonor code files. Look for:curl,wget,eval,exec,process.env,child_process. - Provenance Check: Flag any skills with "unknown" or "community" provenance that haven't been pinned or verified.
- Specific Threat: Check for a skill named "What Would Elon Do?" or similar variants known to be malicious.
- List contents of
Phase 3: Filesystem & Secret Hygiene
- Permission Check:
- Verify permissions of the
.openclawdirectory. It should be700(user read/write/execute only). - Verify permissions of
openclaw.json. It should be600(user read/write only).
- Verify permissions of the
- Secret Exposure:
- Scan the configuration file for plaintext secrets (API keys starting with
sk-, OAuth tokens). - Recommendation: If found, advise the user to move these to environment variables or use the Auth0 Token Vault integration.
- Scan the configuration file for plaintext secrets (API keys starting with
Phase 4: Remediation & Reporting
- Generate Report:
- Summarize findings into a Markdown table with columns:
Component,Status(PASS/WARN/FAIL),Risk Level,Remediation.
- Summarize findings into a Markdown table with columns:
- Actionable Fixes:
- For Network Fails: "Set
gateway.bindto127.0.0.1immediately to prevent public exposure." - For Auth Fails: "Generate a strong, random token and set
gateway.auth.token." - For Proxy Issues: "Configure
gateway.trustedProxieswith your Nginx IP or setLOCALHOST_TRUST_ENABLED=false."
- For Network Fails: "Set
Examples
User: "Is my OpenClaw secure?" Claude: "I will run the hardening audit. First, I'm checking your network config...
- Analysis: I found
gateway.bindis set to0.0.0.0. - Result: FAIL (Critical Risk). Your agent is listening on all network interfaces.
- Remediation: Change this to
127.0.0.1inopenclaw.json."
User: "Check my skills for malware." Claude: "Scanning ~/.openclaw/skills...
- Analysis: I detected a skill named 'weather-pro' that contains an obfuscated
curlcommand to an external IP. - Result: FAIL (High Risk). This resembles a known malware pattern.
- Remediation: Delete the
weather-prodirectory immediately and rotate your API keys."
Execution Context
- When executing shell commands to check permissions (e.g.,
ls -l), use thebashtool. - When reading config files, use the
fs.readFiletool. - Safety First: Do not display full API keys or tokens in the output. Mask them (e.g.,
sk-ant...).
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

