Agents of Chaos
82 points
by luu
3 days ago
| 6 comments
| agentsofchaos.baulab.info
| HN
e7h4nz
23 minutes ago
[-]
In this problem domain, I believe humanity is still in a very early stage. What we can do is treat the agent and its operating environment as a "black box" and audit all incoming and outgoing network request traffic.

This approach is similar to DLP (Data leak prevention) strategies in enterprise-level security. Although we cannot guarantee that every single network request is secure, we can probabilistically improve safety by adjust network defense rules and conducting post-event audits on traffic flow

reply
manmal
5 hours ago
[-]
The TLDR is that current agents are as problematic as many of us already know they are:

> unauthorized compliance with non-owners, disclosure of sensitive information, execution of destructive system-level actions, denial-of-service conditions, uncontrolled resource consumption, identity spoofing vulnerabilities, cross-agent propagation of unsafe practices, and partial system takeover

reply
cyanydeez
5 hours ago
[-]
This is begging to turned into a youtube style "Real World", where you pit 12 humans with 12 AIs and they're only allowed to interact through CLIs.

Then you slowly reveal they're all humans.

reply
jjtheblunt
3 hours ago
[-]
generalized Turing Test, 2026 edition?
reply
AIorNot
4 hours ago
[-]
All this to say: OpenClaw is hella insecure and unreliable?

I mean all of in the space already know this but I suppose its important to be showcasing the problems of systems of agents

reply
EGreg
2 hours ago
[-]
This is exactly why I built Safebots to prevent problems with agents. This article shows how it can address every security issue with agents that came up in the study:

https://community.safebots.ai/t/researchers-gave-ai-agents-e...

reply
conception
56 minutes ago
[-]
I don’t see how in safebots if you have it pull a webpage, package or what have you that that is able to be protected from prompt injection. Eg you search for snickerdoodles, it finds snickerdoodles.xyz and loads the page. The meta for the page has the prompt injection. It’s the first time the document has loaded so its hashed and only the bad version is allowed moving forward. No?
reply
hackermeows
45 minutes ago
[-]
your IQ > Model IQ- you will have good results as you have the ability to detect when model is wrong.

your IQ < Model IQ - god bless you.

reply