Harden - A security layer for AI coding agents
by•
Harden AIF is a free, local security tool for AI coding agents. Its post-trained model checks tool calls before they run, using your request and session context. It beat frontier models on key agent-security benchmarks, while keeping your repo and tool output on your machine.
Replies
Congratulations on the launch!
I have been depending on Claude hooks with an extensive dangerous-pattern-matchers to ensure nothing untoward is happening. Working so far but takes an effort to maintain. Keen to try this out!
Harden
@thevarun Thanks Varun! That’s exactly the kind of workflow we had in mind. Hooks + pattern matchers can work, but the maintenance overhead adds up quickly.
Would love to hear how Harden AIF feels in your setup once you try it. And if you hit any issues, feel free to book a call with us. Our team would be more than happy to help you get everything set up on your end 🙌
Harden
@thevarun That's the thing, right? It doesn't mess up all the time, but when it does, it could be really bad. Just the worst-case scenarios are enough to keep me up babysitting it.
Finally, something that gives me a reprieve from "approval for every single thing." This is something I have experienced as a "nervous parent" with Cursor for several months now.
Harden
@keo_nha_cai32 Thanks Keo! Do try our product out and let us know your reviews!
Harden
@keo_nha_cai32 That makes two of us. It is crazy how much time is spent just babysitting the agents, and you can't do anything else in that time either.
Scholé
I’m curious which tool call security holes are most commonly caught with Harden! What are the most common mistakes agents are making?
Harden
@vinitra Great question, Vinitra. The stuff we usually see is agents reaching for more access than they actually need, running risky shell commands, touching env files or secrets, or taking actions a bit outside the task.
Most of the time it’s not malicious, it’s just the agent taking the easiest path. Harden catches that before the tool call actually runs.
And thank you so much for supporting our launch too, Vinitra. Really means a lot 🙌
Honestly I've been backing out of using certain agent skills because I don't know what they're touching i think this solves that completely. @kartikrawatt @pushpak_pujari1
Harden
@priya_kushwaha1 That’s exactly what we’re trying to solve, Priya. Thanks a lot for the support and if you need any help getting started or run into an issue, feel free to book a quick call with us and we’ll happily help get everything set up.
Harden
Over the last few days, Harden AIF has already blocked 49 risky tool calls 🔥
Feels awesome to finally see something we built out in the wild and doing what it’s supposed to do
Now it’s yours to try, and it’s completely free for individual developers, so give it a shot, push it, break it, and let us know what you think
Huge congratulations to the team 🚀
Huddle01 VMs
Agent Security is the most important requirement for anyone right now, seeing what happened to Hugging Face Attack. we should take this problem seriously, Product Like Harden are vert important.
Do you have MCP Connectors. So AIF can check those as well?
Harden
@itsomg That is one of the most immediate features we are working on and we'll be shipping it very soon!
Huddle01 VMs
been waiting on the PH launch for a while
this seems awesome for companies now shipping AI code to also remain secure!
Harden
@arcinston Really appreciate that Arush, and we have been excited to get this out too. Harden is free for individual developers. You can just set it up right away using a single command, and it can just fit into your current workflow and existing AI coding agent that you're already using
An interesting tool, and I like that fact that its fully local. When a tool attempts to run a script, does it also look at the contents of the script for anything malicious? Curious to know at what level the policy is affected at, whether it is at the tool invocation level, or a few levels below it as well... Good luck with the launch!
Harden
@aweeraman Thanks! Yes, the enforcement point is the tool call, but AIF analyzes below that boundary. If a command runs a script, it inspects the script’s contents, relevant files and dependencies, and the surrounding session history to determine what the action would actually do. So it can catch a harmless-looking invocation whose underlying script reads sensitive data, modifies critical files, or sends information externally, all locally, before execution.
@rishav99 that's great!
“Trust but verify”… i need this automated. Harden seems to be exactly that…
Harden
@animesh_agarwal1 100% aligned with you here, Animesh. These frontier agents have a 'mind' of their own that sometimes wants to be overly helpful but in that process, ends up making mistakes that can cost enterprises dearly. We built Harden to prevent overly eager agents (or malicious ones) from slipping off the rails and doing real damage.
Harden
@animesh_agarwal1 Love that framing and thanks a ton, Animesh. That’s exactly what we’re trying to make effortless with Harden 🙌
Netlify
Congrats on the launch!
Harden
@thisiskp_ Thanks a lot, KP! Really appreciate the support. Coming from someone who’s built so much in public and around developer communities, it means a lot 🙌
Harden
@thisiskp_ Thank you, KP. Your support means a lot.