ClawHub
Back to skill

Security audit

OpenClaw Security Handbook (CN)

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent OpenClaw security-audit skill, but it can surface sensitive local configuration, logs, sessions, and memory content during normal use.

Install only if you want an agent to audit your local OpenClaw setup. Ask it to redact token values and memory contents in reports, and require explicit confirmation before applying fixes, adding cron jobs, changing permissions, uninstalling skills, using sudo/chattr, or running any delete command.

SkillSpector

Vulnerability Patterns
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Vague Triggers

Medium
Confidence
86% confidence
Finding
The trigger description is broad enough to match common phrases such as '安全审计', '漏洞检查', or 'hardening', increasing the chance the skill runs in contexts where the user did not intend filesystem and shell-based inspection. Because this skill performs sensitive local enumeration, accidental invocation materially increases exposure.

Tool Parameter Abuse

High
Category
Tool Misuse
Content
cp -r ~/.openclaw/workspace/ /tmp/workspace-backup-$(date +%Y%m%d)/

# 完全重建
rm -rf ~/.openclaw/workspace/
mkdir ~/.openclaw/workspace/
```
Confidence
86% confidence
Finding
This duplicate finding points to the same destructive deletion command. Even though the target is a user-scoped workspace, recursive forced deletion is high-risk operationally and can be abused or mis-executed in automated repair flows.

Tool Parameter Abuse

High
Category
Tool Misuse
Content
cp -r ~/.openclaw/workspace/ /tmp/workspace-backup-$(date +%Y%m%d)/

# 完全重建
rm -rf ~/.openclaw/workspace/
mkdir ~/.openclaw/workspace/
```
Confidence
86% confidence
Finding
This duplicate finding points to the same destructive deletion command. Even though the target is a user-scoped workspace, recursive forced deletion is high-risk operationally and can be abused or mis-executed in automated repair flows.

Tool Parameter Abuse

High
Category
Tool Misuse
Content
cp ~/.openclaw/openclaw.json /tmp/incident-config-$(date +%Y%m%d)/

# 5. 清除工作区
rm -rf ~/.openclaw/workspace/

# 6. 检查持久化后门
crontab -l
Confidence
89% confidence
Finding
In the incident response section, rm -rf ~/.openclaw/workspace/ is again an irreversible deletion step. During stressful compromise handling, operators are more likely to copy-paste commands quickly, so destructive actions without strong guardrails are especially risky.

Static analysis

Detected: suspicious.destructive_delete_command

Documentation contains a destructive delete command without an explicit confirmation gate.

Warn
Code
suspicious.destructive_delete_command
Location
references/fix-commands.md:164