Metraipolis › archive › dc_a9fa7d3899fd

Tracekit Box: Running AI Agents in Micro-VMs Where Every Way Out Is Decided and Signed — arXiv:2610.38458

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.38458
License (as archived)
CC0-1.0
Archived
2026-10-31T06:12:46.571Z
SHA-256 of the archived text
57587aa6eb008e0c4a9250267ce3e375279b5bff79a3b2d750f564c736c1cc16
Stable URL of this page
https://metraipolis.com/documento/dc_a9fa7d3899fd

How to cite

Tracekit Box: Running AI Agents in Micro-VMs Where Every Way Out Is Decided and Signed — arXiv:2610.38458 — arXiv (en), https://arxiv.org/abs/2610.38458 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a9fa7d3899fd (Metraipolis archive dc_a9fa7d3899fd, sha256 57587aa6eb008e0c4a9250267ce3e375279b5bff79a3b2d750f564c736c1cc16)
BibTeX
@misc{dca9fa7d3899fd,
  title = {Tracekit Box: Running AI Agents in Micro-VMs Where Every Way Out Is Decided and Signed — arXiv:2610.38458},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.38458},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a9fa7d3899fd; sha256 57587aa6eb008e0c4a9250267ce3e375279b5bff79a3b2d750f564c736c1cc16},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.38458. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

AI agents now install packages, call model APIs with their operators' keys and change code in repositories that deploy to production. The network, credentials and write access they need are also how they can leak data, steal a key or change a system nobody approved. Sandboxes contain an agent but leave little evidence of what crossed their boundary; tracing records what happened but contains nothing. We present Tracekit Box, an open-source system (MIT, v0) that does both. Each job runs in its own Firecracker micro-VM with no network card. The only ways out are doors on the host, served over vsock: commands, outbound connections, secrets, model calls and the workspace patch. At every door a Tracekit signer the agent cannot reach decides what passes and signs it into one run per box. Names are resolved on the host; private and cloud-metadata addresses are always refused; secrets never enter the VM, which sees placeholders the host proxy swaps for real values only in one header for bound hosts; and changes come back as a patch applied file by file after the signer decides each file. Box fails closed, and each job ends as a .tkb bundle anyone can verify offline. All 13 end-to-end checks pass on a real KVM runner (the test that runs them takes 28.5 s, including image pull and boot); 15 fuzz targets on the trust boundary produced nine findings, all fixed; and the demo run's 102 signed records verify. Box does not yet run Firecracker's jailer, needs a co-located signer, and records processes inside the VM only where they cross a door.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computational Engineering, Finance, and Science (cs.CE) ; Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR); Operating Systems (cs.OS).
Pagina del lavoro: https://arxiv.org/abs/2610.38458 — 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 2026-10-31T06:07:08.659Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).