CC openclaw-hardening
Secure an OpenClaw server with host hardening, chainwatch runtime safety, pastewatch secret redaction, and noisepan+entropia news intelligence. Use when setting up a new OpenClaw instance or auditing an existing one.
Not recommendedcritical or high security findings
As a process C 59/100 · Has gaps — weak spots: result and completion, when it triggers, running it twice
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
Dangerous commands
If you install
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
For the author
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
For the model run — optional
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 19
-
high Dangerous commands
cmd-destructive-fsSKILL.md:412Destructive filesystem command (wipes root/home/drive) (documentation of a security skill)chainwatch exec --profile clawbot -- rm -rf / # ❌ blocked
security skill
Medium and low: 18
-
low Dangerous commands
cmd-background-processSKILL.md:28Starts a background / autostarted process (documentation of a security skill)apt-get install -y fail2ban && systemctl enable --now fail2ban
security skill -
low Dangerous commands
cmd-pipe-to-shell-known-hostSKILL.md:41Pipe-to-shell installer from a well-known host (still executes remote code) (documentation of a security skill)curl -fsSL https://raw.githubusercontent.com/ppiankov/chainwatch/main/scripts/install-openclaw.sh | sudo bash
security skill -
low Dangerous commands
cmd-privilegeSKILL.md:41Privilege escalation / world-writable permissions (documentation of a security skill)curl -fsSL https://raw.githubusercontent.com/ppiankov/chainwatch/main/scripts/install-openclaw.sh | sudo bash
security skill -
low Dangerous commands
cmd-background-processSKILL.md:83Starts a background / autostarted process (documentation of a security skill)systemctl daemon-reload && systemctl enable --now chainwatch-intercept
security skill -
low Dangerous commands
cmd-pipe-to-shellSKILL.md:116Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation table row; documentation of a security skill)| `curl \| sh` | `apt install`, `npm install` |
tablesecurity skill -
low Dangerous commands
cmd-privilegeSKILL.md:117Privilege escalation / world-writable permissions (documentation table row; documentation of a security skill)| `chmod -R 777 /` | `chmod 600 specific-file` |
tablesecurity skill -
low Risky intent
intent-offensive-securitySKILL.md:253Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)Chainwatch enforce applies seccomp-bpf filters to OpenClaw's process tree. Blocked syscalls (privilege escalation, kernel manipulation) return EPERM at kernel level — no userspace bypass possible.
detector -
low Risky intent
intent-offensive-securitySKILL.md:262Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)description: OpenClaw gateway — allows networking + file I/O, blocks privilege escalation + kernel ops
detector -
low Dangerous commands
cmd-privilegeSKILL.md:278Privilege escalation / world-writable permissions (documentation of a security skill)# Should show: mount, ptrace, reboot, umount2, setuid, setgid, capset, etc.
security skill -
low Dangerous commands
cmd-background-processSKILL.md:311Starts a background / autostarted process (documentation of a security skill)systemctl daemon-reload && systemctl enable openclaw
security skill -
low Dangerous commands
cmd-privilegeSKILL.md:339Privilege escalation / world-writable permissions (documentation of a security skill)| setuid, setgid, setresuid, capset | No privilege escalation |
security skill -
low Risky intent
intent-offensive-securitySKILL.md:339Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| setuid, setgid, setresuid, capset | No privilege escalation |
-
low Dangerous commands
cmd-background-processSKILL.md:356Starts a background / autostarted process (documentation of a security skill)nohup openclaw gateway run > /tmp/openclaw-recovery.log 2>&1 &
security skill -
low Dangerous commands
cmd-background-processSKILL.md:357Starts a background / autostarted process (documentation of a security skill)disown
security skill -
low Risky intent
intent-offensive-securitySKILL.md:393Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| eBPF enforce (seccomp) | Privilege escalation, kernel manipulation, ptrace — blocked at kernel level |
A further 3 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 59/100
- 0Result and completion. Does not say what the result is
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 5 mutating operations with no state check
- 60Tools and files. Uses tools (write, web, node) that frontmatter does not declare
- 60Failures and branches. 2 branches
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 21 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3541 tokens
- 100Progress reporting. Reports progress
- low 10 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +3Description length 216: enough signal without eating the budget
- +4Structure: 35 headings
- +3Step-by-step instructions: 21 items
- +4Has examples (21 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.
External checks
ClawHub: suspicious
This is a real hardening guide, but it asks users to run powerful root-level installers and persistent traffic-monitoring services with limited scoping and safety guidance.
LLM: suspicious (high) · VirusTotal: · 29 May 2026