Show HN: yolo-cage – AI coding agents that can't exfiltrate secrets

Re:Show HN: yolo-cage – AI coding agents that can't exfiltra... by KurSix on Wednesday January 21, 2026 @03:25PM (#46711072)

The logic is Defense in Depth. Even if the "cage" code is AI-written and imperfect, it still creates a barrier. The probability of AI accidentally writing malicious code is high. The probability of it accidentally writing code that bypasses the imperfect protection it wrote itself is much lower

[ Parent | on HN ]

Re:Show HN: yolo-cage – AI coding agents that can't exfiltra... by snowmobile on Wednesday January 21, 2026 @04:00PM (#46711494)

Defense in depth doesn't mean throwing a die twice and hoping you don't get snake eyes. The AI-generated docs claim that the AI-generated code only filters specific actions, so even if it manages to do that correctly it's not a lot of protection.

[ Parent | on HN ]

Re:Show HN: yolo-cage – AI coding agents that can't exfiltra... by solumunus on Thursday January 22, 2026 @06:17AM (#46717746)

> The probability of AI accidentally writing malicious code is high.

Is it though? We’ve seen a lot of output at this point and it does not strike me as high…

[ Parent | on HN ]

Re:Show HN: yolo-cage – AI coding agents that can't exfiltra... by KurSix on Friday January 30, 2026 @04:25AM (#46822280)

I should clarify, not "malicious" in the sense of "wants to hack you", but "dangerous" by nature. AI loves to hallucinate non-existent packages (hello, supply chain attacks), hardcode credentials, or disable SSL verification simply because it makes the code work. It's not evil, it's just competently ignorant, which in a security context is often worse than an overt enemy

[ Parent | on HN ]