DigiNews

Tech Watch by Johan Denoyer

← Back to articles

Show HN: Scan your AI agents for dangerous capabilities

Quality: 8/10 Relevance: 9/10

Summary

MakerChecker presents an open-source security layer for AI agents that enforces deny-by-default governance and maintains a cryptographically signed audit trail. It covers scanning agent capabilities, wrapping tools with governance primitives, and optional self-hosted servers for auditable, tamper-evident decision logs to prevent agents from approving their own work.

🚀 Service construit par Johan Denoyer