⛔
Security Alert:This skill has been flagged for potential malicious behavior. Installation is blocked.
secucheck
⛔Blocked·Scanned 2/18/2026
Dangerous skill: executes local audit scripts (bash ~/.openclaw/skills/secucheck/scripts/full_audit.sh) and starts a network‑accessible server (python3 -m http.server --bind 0.0.0.0). It proclaims Read-only / Never modifies configuration automatically while skill.json grants exec and gateway.
from clawhub.ai·v22f9f29·155.7 KB·0 installs
Scanned from 2.8.0 at 22f9f29 · Transparency log ↗
$ vett add clawhub.ai/jooneyp/secucheckInstallation blocked
🔒 secucheck
Comprehensive security audit skill for OpenClaw
Analyzes configuration, permissions, exposure risks, and runtime environment with context-aware recommendations.
Installation
clawhub install secucheck
Usage
Ask your OpenClaw agent:
security audit
Or:
secucheckrun security checkaudit my setup
Expertise Levels
On first run, you'll be asked to choose a level:
| Level | Description |
|---|---|
| 🌱 Beginner | Simple analogies, no jargon |
| 💻 Intermediate | Technical details, config examples |
| 🔐 Expert | Attack vectors + edge cases |
All levels run identical checks—only explanation depth varies.
What It Checks
- ⚡ Runtime: Network exposure, VPN, containers, privileges
- 📢 Channels: DM policies, group policies, mention settings
- 🤖 Agents: Tool permissions, workspace isolation
- ⏰ Cron Jobs: Automated tasks, external data dependencies
- 🧩 Skills: Installed skill security scan
- 🔐 Sessions: Session isolation, memory settings
- 🌐 Network: Gateway binding, authentication
Dashboard
Visual HTML report:
show dashboard
Displays:
- Overall security score
- Runtime environment status
- Findings by severity with collapsible details
Auto-Review
This skill runs automatically when:
- Installing new skills
- Creating/modifying agents
- Creating/modifying cron jobs
Risk Levels
| Icon | Severity | Meaning |
|---|---|---|
| 🔴 | Critical | Immediate action required |
| 🟠 | High | Significant risk, fix soon |
| 🟡 | Medium | Notable concern |
| 🟢 | Low | Minor issue or best practice |
| ⚪ | Info | Not a risk, but notable |
Context-Aware
secucheck considers your environment:
- VPN/Tailscale? Network findings less critical
- Single user? Session isolation less important
- Containerized? Privilege escalation less severe
Example Output
🔒 Security Audit Results
🟢 Good
| Severity | Count |
|----------|-------|
| 🔴 Critical | 0 |
| 🟠 High | 0 |
| 🟡 Medium | 1 |
| 🟢 Low | 2 |
Runtime: VPN active ✅ | No container | sudo available
Safe by Design
- Read-only: Never modifies configuration automatically
- Explicit consent: All fixes require user confirmation
- Impact warnings: Explains what might break before applying
License
MIT
Author
joon & OpenClaw Agent