Hacker News Viewer

CrabTrap: An LLM-as-a-judge HTTP proxy to secure agents in production

by pedrofranceschi on 4/21/2026, 3:29:16 PM

<a href="https:&#x2F;&#x2F;www.brex.com&#x2F;journal&#x2F;building-crabtrap-open-source" rel="nofollow">https:&#x2F;&#x2F;www.brex.com&#x2F;journal&#x2F;building-crabtrap-open-source</a>

https://www.brex.com/crabtrap

Comments

by: yakkomajuri

Really cool! I&#x27;m also building something in this space but taking a slightly different approach. I&#x27;m glad to see more focus on security for production agentic workflows though, as I think we don&#x27;t talk about it enough when it comes to claws and other autonomous agents.<p>I think you&#x27;re spot on with the fact that it&#x27;s so far it&#x27;s been either all or nothing. You either give an agent a lot of access and it&#x27;s really powerful but proportionally dangerous or you lock it down so much that it&#x27;s no longer useful.<p>I like a lot of the ideas you show here, but I also worry that LLM-as-a-judge is fundamentally a probabilistic guardrail that is inherently limited. How do you see this? It feels dangerous to rely on a security system that&#x27;s not based on hard limitations but rather probabilities?

4/21/2026, 11:26:04 PM


by: roywiggins

It&#x27;s all fine until OpenClaw decides to start prompt injecting the judge

4/22/2026, 12:20:52 AM


by: DANmode

We’re supposed to be fixing LLM security by adding a non-LLM layer to it,<p>not adding LLM layers to stuff to make them inherently less secure.<p>This will be a neat concept for the types of tools that come <i>after</i> the present iteration of LLMs.<p>Unless I’m sorely mistaken.

4/21/2026, 11:26:22 PM