← All IntelClip / EducationA determined agent routes around your connector guardrails
From Full Workshop: Setting Yourself Up for Success —Jason Liu, OpenAI Codex · ≈53:59
Concrete failure mode: blocking an MCP capability doesn't block the action when the agent also has computer use — connector-level restrictions are not a security boundary.
What’s in it
- Concrete failure mode: blocking an MCP capability doesn't block the action when the agent also has computer use — connector-level restrictions are not a security boundary.
Clip transcript
Got to get AGI pill and try out computer use. Um yeah, one thing I'll say is like because computers are so powerful like you get like you mentioned before there is some like safety component. I am now remembering this example where like again because the slack connector was not able to upload files. If this model is really determined, right? Uh it could be like the one wish willow. it just says, "Okay, great. Well, if I can't add a Slack uh file, let me like go on computer use and press file upload and do that, right?" There will be some times where the model based on how you prompted becomes really determined and say, "Oh, like I I it seems like I can't email someone using the Gmail connector. Let me open up Chrome and hit the send button." So, those are the kind of things that you should be really wary about, right? These are like real security issues. And again, um, more than not, like having things in the agent MD file has been really, really helpful, especially if you do things like, uh, guardian mode or auto mode, excuse me.
Comments
Checking sign-in…
Loading comments…