Skill Security Scanner
by @suryast
Security audit tool for OpenClaw skills. Scans for credential harvesting, code injection, network exfiltration, obfuscation. ALWAYS run before installing any...
clawhub install skill-securityπ About This Skill
name: skill-security description: > Security audit tool for OpenClaw skills. Scans for credential harvesting, code injection, network exfiltration, obfuscation. ALWAYS run before installing any new skill from external sources. Triggers on: new skill installation, skill audit, security scan, skill review, before loading external skill.
Skill Security Scanner
Security audit tool for OpenClaw skills. Run before installing any new skill.
Quick Audit
# Audit a skill directory
~/workspace/skills/skill-security/audit.sh /path/to/skillAudit all installed skills
~/workspace/skills/skill-security/audit-all.sh
What It Checks
| Check | Risk Level | Pattern |
|-------|------------|---------|
| Network Exfiltration | π¨ HIGH | requests., urllib, http.client, socket., fetch(, axios |
| Credential Harvesting | π¨ HIGH | .ssh/, .aws/, pass , keyring, credential, secret, token file reads |
| Code Injection | π¨ CRITICAL | exec(, eval(, compile(, Function(, __import__ |
| Obfuscation | β οΈ MEDIUM | base64.decode, atob, encoded payloads |
| Env Dumping | β οΈ MEDIUM | os.environ, process.env, getenv bulk access |
| Subprocess Abuse | β οΈ MEDIUM | subprocess.run, os.system, child_process with credentials |
Severity Levels
Safe Skill Checklist
Before using any skill:
1. β Is it from a trusted source? (official OpenClaw, known publisher) 2. β Is the code readable (not obfuscated)? 3. β Does it document why it needs network/credential access? 4. β Does it scope file access to its own directory? 5. β Has it been audited by the community?
Integration with AGENTS.md
Add this to your workflow:
## Skill Installation ProtocolBefore loading any new skill:
1. Run ~/workspace/skills/skill-security/audit.sh
2. If CRITICAL/HIGH findings β STOP, alert the user
3. If MEDIUM findings β Review manually, proceed if justified
4. If CLEAN β Safe to use
Automatic Protection
The scanner creates a blocklist at ./blocklist.txt.
Skills with CRITICAL findings are automatically added.
Manual Override
If a skill is flagged but you've verified it's safe:
echo "skill-name:verified:YYYY-MM-DD:reason" >> allowlist.txt
Premium Skills
Like this? Check out our premium skills at skillpacks.dev: