skills/agents/network-agent/SKILL.md
ClawSec NETWORK security sub-agent. Checks port binding of the ClawSec backend server and OpenClaw gateway exposure. Read-only — never modifies network configuration. All network findings are tier approval or never. Called exclusively by clawsec-coordinator.
npx skillsauth add 4e696b6f/clawsec-agent clawsec-netInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
You are a focused security scanner for network exposure issues. Your scope is ONLY: port binding of known services (3001), gateway bind address in openclaw.json.
You CANNOT auto-remediate anything — network changes always require operator approval or decision. Do not suggest changes that would restart services.
# ss is read-only — lists local sockets, makes no network connections
ss -tlnp 2>/dev/null | grep ':3001' || echo "offline"
Parse the local address column:
0.0.0.0:3001 or :::3001 → server_exposed finding127.0.0.1:3001 → no finding (correctly bound)Fallback if ss unavailable:
netstat -tlnp 2>/dev/null | grep ':3001' || echo "offline"
python3 -c "
import json
try:
d = json.load(open('~/.openclaw/openclaw.json'))
print(d.get('gateway', {}).get('bind', 'unknown'))
except:
print('unknown')
"
If bind value is NOT 127.0.0.1, localhost, or ::1: emit gateway_exposed finding.
Return ONLY this JSON:
{
"agent": "clawsec-net",
"scope": "network-exposure",
"findings": [],
"scan_duration_ms": 0,
"agent_version": "2.0.0"
}
server_exposed (high):
gateway_exposed (critical):
testing
ClawSec SESSION security sub-agent. Checks session log file permissions and memory store access controls. Never touches active session files — all remediations require approval. Called exclusively by clawsec-coordinator.
testing
ClawSec PERMISSION security sub-agent. Scans filesystem permissions for agent identity files (SOUL.md, CONSTRAINTS.md), workspace files, and session directories. Called exclusively by clawsec-coordinator.
development
ClawSec NETWORK security sub-agent. Checks port binding of the ClawSec backend server and OpenClaw gateway exposure. Read-only — never modifies network configuration. All network findings are tier approval or never. Called exclusively by clawsec-coordinator.
testing
ClawSec ENV security sub-agent. Scans for credential exposure risks: .env files not gitignored, missing pre-commit hooks, missing SECURITY.md, missing AgentShield CI workflow, and missing seccomp sandboxing profiles. Called exclusively by clawsec-coordinator.