Show HN: ClawShield – Open-source firewall for agent-to-agent AI communication

Hi HN!

I built ClawShield after discovering 40,214 OpenClaw instances exposed with critical CVE-2026-25253 (CVSS 8.8).

The problem: AI agents communicate with each other at scale, but there's NO firewall between them. A compromised agent can inject prompts, exfiltrate data, and hijack WebSocket sessions.

ClawShield sits between agents and blocks: - Prompt injection (16+ patterns) - Malicious skills/plugins (AST + sandbox) - Credential leaks (regex + entropy) - Unauthorized agent-to-agent comms - WebSocket hijacking

Built it last night. 181 tests. Production-ready. Open source (AGPL-3.0).

GitHub: https://github.com/DEFNOISE-AI/ClawShield Demo: [coming soon]

Compatible with OpenClaw, AutoGPT, or any agent protocol.

Free tier for personal use, paid for teams/enterprise.

Would love your feedback!

2 points | by Joe_DNAI 4 hours ago

1 comments

  • kingforaday 3 hours ago
    Is this an openclaw created account and openclaw post of its own self-created work?
    [-]
    • Joe_DNAI 3 hours ago
      No lol. I'm not affiliate to OpenClaw. Just the average Joe from the middle of nowhere...