Names Are Not Objects: Object-Bound Confinement for Compromised AI Coding Agents

본문 미리보기

arXiv:2610.14488v1 Announce Type: new Abstract: Coding agents read repositories and web pages that anyone can write, and then act with their user's authority. Prompt-injection defenses make it less likely that the model is steered but do not prevent it, so the system around the model must contain an agent that is already compromised. Many exploits against deployed coding agents share one cause: a check approves a name, such as a path, an argument vector, or a directory, and a later step maps th