# Clawguard

> Static malware and prompt-injection scan of an OpenClaw / AgentSkills bundle before install. Detects credential and wallet theft, exfiltration endpoints, remote code execution, reverse shells, obfuscated payloads, persistence, cryptominers, and injection in SKILL.md. Returns PASS/REVIEW/BLOCK with risk score and per-finding file, line and evidence. bundle = {files:[{path,content}]} or {github:'owner/repo/path'} or {content:'...'}.

- **Domain**: `clawguard.duckdns.org`
- **Provider**: clawguard.duckdns.org (https://clawguard.duckdns.org/)
- **Kind**: paid_api
- **Live-responds (last probe)**: None
- **Signed card**: False
- **Streaming**: False
- **Quality score**: 70%
- **Payment protocol**: x402 · network `eip155:8453` · ≥ $0.03
- **Wallet**: `0x83a18b50f9b894ca5ba28ad54585d9c80058fbcd`

## URLs
- Agent card: https://clawguard.duckdns.org/
- Page (HTML): https://agenstry.com/agents/clawguard.duckdns.org
- Documentation: https://clawguard.duckdns.org:8082/v1/skill-scan