HN Explorer

yusufjacobs

↗ HN profile [ 16.4 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Show HN: We scanned 500 ClawHub skills for security risks – 10% were dangerous

    We built tork-scan, a free open-source CLI that checks AI agent skills (MCP tools) for 19 security risk patterns — reverse shells, credential harvesting, base64 payloads, eval(), C2 domains, and more. We pointed it at…

    3 points 1
  2. Show HN: Tork – Open-source AI governance layer, 11 SDKs& 116 framework adapters (tork.network)

    Been working on this solo for a while. Tork is a governance middleware that sits between AI agents and the tools they call — intercepting every interaction to apply PII redaction, policy enforcement, and compliance…

    1 points 0