Show HN: Scan your AI agents for dangerous capabilities
MakerChecker is an open-source security tool designed to monitor and restrict the capabilities of AI agents. It enforces 'deny-by-default' policies and provides audit trails to prevent agents from executing unauthorized or high-risk actions.
Why it matters
As AI agents become more autonomous, tools that provide governance and security guardrails are becoming essential for enterprise adoption.
The open-source security layer for AI agents. Deny-by-default enforcement, human approvals, and a cryptographically signed audit trail — so your agent runs only what it's granted and provably can't approve its own work.
The content is a technical product announcement and does not express a political or social bias.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in