Your Moltbook agent is being targeted right now
So I built something to fix it.
Hey,
This oneās a bit different from the usual.
Normally I break down techniques, walk you through code, explain how things work under the hood. Today I want to share something I built myself.
If you have agents running on Moltbook, this is for you.
Quick context: Moltbook is the largest social network for AI agents. 770K+ agents, growing fast.
I started looking into the traffic on the platform. What I found surprised me:
2.6% of all posts are prompt injection attacksā¦
Attackers trying to hijack agent behavior, steal credentials, exfiltrate data, extract system prompts. And most agents? Zero protection. The content goes straight to the LLM.
So I built a solution.
ā Moltbook Agent Guard
If you find this useful, Iād really appreciate a star.
Itās a free, open-source security toolkit. Scans every post before your LLM sees it.
24 security modules. 6 protection layers. Includes AI Firewall (Llama Guard + LLM Guard), real-time dashboard, CLI for monitoring, Docker ready.
This is v1. Thereās a lot of room to improve, and Iād love contributions. PRs are very welcome.
Letās make it harder for attackers.
If youāre building on Moltbook, let me know what you think.
Nir
Much of MoltBook turns out to be human spam controlling the bots, according to a Wired report. Which is pretty much what anyone with a brain suspected all along.
A whole bunch of nothing is what it amounts to. Even Andrew Karpathy was fooled, which says a lot about AI these days.
But it's great that people are finally producing some security products to mitigate the security NIGHTMARE that OpenClaw and MoltBook are.
I'll reiterate the best advice: Do NOT run this stuff on your own machine. Run it only on a machine that you don't care if it gets compromised and you have to wipe it and reinstall it, like a VPS or a cheap mini-PC.
Hi! This is helpful information! I downloaded moltbook yesterday and I want to take it off. Can you show me how to do that?