OpenAlex ·
Names Are Not Objects: Object-Bound Confinement for Compromised AI Coding Agents
- Published
- Source
- OpenAlex
- Published in
- arXiv (Cornell University)
- DOI
- 10.48550/arxiv.2610.14488
- Original
- Read it at the publisher
- Topics
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 that name to a different object: the file behind a symlink, the behavior an option selects, or a repository that git discovers on its own. We present Zero-Trust Agent Cells (ZTAC). A cell runs the agent in a kernel sandbox whose only route to files, programs, and the network is a socket to a broker. The broker resolves each request to the object it will act on, decides on that object, and checks at use that it is acting on the object it authorized. Programs that the broker starts run in a sandbox compiled from the same policy, and approvals are bound to the resolved object and can be used once. Our macOS prototype has 3.2k lines of trusted Rust code, excluding dependencies. We evaluate it against 74 attacks with ground-truth oracles, including replays of 10 publicly disclosed incidents. A tool allowlist loses 66 of them, and an allowlist combined with the kind of command sandbox that deployed agents use loses 56. ZTAC loses 2, both of which encode a secret into traffic to an allowed endpoint, and holds 14 for review. It completes 43 of 46 benign operations, with 8 approval prompts, and 4 of 7 workflows. A no-op brokered request has a median latency of 4.0 ms, and the spawned programs we measured take 8.5 ms to 18.4 ms longer than without ZTAC.
The authors’ abstract, as arXiv lists it. arXiv’s listings, abstracts included, are free for anyone to reuse.
Read it on ReadSearch
Each opens after you create an account, and brings you back to this paper.
More in Artificial Intelligence
MoSAIC: Learning DAG Scheduling Heuristics from Optimal Schedules through Motif-Aware Recovery and LLM-Guided Reasoning
Stateless Stochastic Computing for Generative AI on Superconducting Logic: A Model-Hardware Co-Design
Heterogeneous Structured Pruning Under Resource Constraints for Hardware-Efficient Large Language Models
A Hardware-Native Trapped-Ion Hybrid Qudit-Oscillator Instruction Set
SafeDSE: Joint Exploration of Safety Architecture Patterns, Mapping, and Scheduling for Dataflow Applications With Safety Arguments (Extended Version)
Get the few papers worth your time in Artificial Intelligence every morning.
ReadSearch reads the new papers in your field each day and brings you the few worth reading, each with its key finding in a sentence.