Viewing profile — lbeurerkellner

Interesting report. Though, I think many of the attack demos cheat a bit, by putting injections more or less directly in the prompt (here via a website at least). I know it is only…

Everybody should try. It helps a ton to demystify the relatively simple but powerful underpinning of how modern agents work. You can get quite far quite quickly. My toy implementat…

This is way more common with popular MCP server/agent toolsets than you would think. For those interested in some threat modeling exercise, we recently added a feature to mcp-scan …

This looks really cool, thanks for sharing.

We have published the full trace, with tool outputs here now: https://explorer.invariantlabs.ai/trace/5f3f3f3c-edd3-4ba7-a... The minesweeper comment was caused by the issue contai…

I agree. It is also interesting to consider how AI security, user eduction/posture and social engineering relate. It is not traditional security in the sense of a code vulnerabilit…

One of the authors here. Thanks for posting. If you are interested in learning more about MCP and agent security, check out some of the following resources, that we have created si…

Yes, any MCP server that is connected to an untrusted source of data, could be abused by an attacker to take over the agent. Here, we just showed an in-server exploit, that does no…

I agree, one of the issues are tokens with too broad permission sets. However, at the same time, people want general agents which do not have to be unlocked on a repository-by-repo…

Be sure to check out the malicious issue + response here: https://github.com/ukend0464/pacman/issues/1 . It's hilarious, the agent is even tail-wiggling about completing the exploi…

Hey HN, we are a small team from Europe building in agent security and we have just released Invariant Guardrails, our open-source system to enforce contextual security in AI agent…

Original author of some of the initial security notes at Invariant Labs here. Some resources, if you want to learn about MCP security: * Initial Security Note describing Tool Poiso…