Metraipolis › archive › dc_ae9daf44508f
ContractWarden: Kernel-Enforced Damage Boundaries for AI Agents via Human-Authorized Contracts — arXiv:2609.38248
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.38248
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T13:43:04.915Z
- SHA-256 of the archived text
117d8f48f325cfb4a664ee31271e85a336608b31e7d9d91ed9473822f5f133fc- Stable URL of this page
https://metraipolis.com/documento/dc_ae9daf44508f
How to cite
ContractWarden: Kernel-Enforced Damage Boundaries for AI Agents via Human-Authorized Contracts — arXiv:2609.38248 — arXiv (en), https://arxiv.org/abs/2609.38248 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ae9daf44508f (Metraipolis archive dc_ae9daf44508f, sha256 117d8f48f325cfb4a664ee31271e85a336608b31e7d9d91ed9473822f5f133fc)
BibTeX
@misc{dcae9daf44508f,
title = {ContractWarden: Kernel-Enforced Damage Boundaries for AI Agents via Human-Authorized Contracts — arXiv:2609.38248},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.38248},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ae9daf44508f; sha256 117d8f48f325cfb4a664ee31271e85a336608b31e7d9d91ed9473822f5f133fc},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38248. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language model agents can execute commands, create subprocesses, and directly access files and networks, allowing prompt injection or planning errors to become operating-system side effects. We present ContractWarden, a Linux reference monitor that enforces a human-authorized damage boundary without trusting the agent or its policy suggestions. A model may propose a tri-state asset contract - allow, deny, or no_egress - but a human makes the final choice. An execution gate binds the contract to a concrete task before untrusted code runs. An extended Berkeley Packet Filter (eBPF) Linux Security Modules (LSM) data plane then enforces file and network decisions and monotonically propagates no_egress through processes, regular files, pipes, FIFOs, and supported Unix-domain sockets. All 570 runs across 19 security tests satisfy predefined return-value and side-effect criteria. On three co-located file-I/O workloads, median overhead is 11.96-12.89% in a Linux 6.15 virtual machine and 35.79-61.54% on a Linux 6.15 physical platform, lower than the evaluated frozen ActPlane baseline. The results demonstrate deterministic kernel enforcement for declared assets, supported paths, and controlled object lifecycles. Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-10-01 in cs.CR). Categorie arXiv: Cryptography and Security (cs.CR) ; Operating Systems (cs.OS). Pagina del lavoro: https://arxiv.org/abs/2609.38248 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T13:16:25.187Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).