Metraipolis › archive › dc_877ad3e81e76

Weird Machine Compositors: Exploiting AI Orchestration at the Expression Layer — arXiv:2609.33413

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.33413
License (as archived)
CC0-1.0
Archived
2026-10-07T22:34:38.547Z
SHA-256 of the archived text
3358ba644d6d9c8468bcabe549b67997b9b9ac1dc6bcf8bf6961b7d880b8b361
Stable URL of this page
https://metraipolis.com/documento/dc_877ad3e81e76

How to cite

Weird Machine Compositors: Exploiting AI Orchestration at the Expression Layer — arXiv:2609.33413 — arXiv (en), https://arxiv.org/abs/2609.33413 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_877ad3e81e76 (Metraipolis archive dc_877ad3e81e76, sha256 3358ba644d6d9c8468bcabe549b67997b9b9ac1dc6bcf8bf6961b7d880b8b361)
BibTeX
@misc{dc877ad3e81e76,
  title = {Weird Machine Compositors: Exploiting AI Orchestration at the Expression Layer — arXiv:2609.33413},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.33413},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_877ad3e81e76; sha256 3358ba644d6d9c8468bcabe549b67997b9b9ac1dc6bcf8bf6961b7d880b8b361},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33413. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Orchestration platforms secure user-provided expressions through enumerate and block sandboxing: AST rewriting, runtime property blocklists, template sandbox environments. We demonstrate that these sandboxes are weird machines whose instruction set is the underlying language specification, and that the enumerate and block approach is unfixable, following the same trajectory that led to the deprecation of past sandboxing technologies such as Java's SecurityManager and vm2. We validate this claim through three rounds of escalating bypasses against n8n's expression sandbox (three CVEs, two CVSS 9.4, one unauthenticated), and frame these findings within a broader pattern of sandbox failures across the orchestration products category. We identify a trust laundering pattern where orchestration pipelines and applications move attacker controlled input from untrusted to fully credentialed through transformations that strip taint at each level. AI-assisted enumeration accelerates the discovery of these coverage gaps, compressing the timeline between a sandbox's deployment and its compromise. We provide an AST coverage analysis methodology, an accompanying open-source tool, and a defensive playbook that includes policy inversion (allowlist over blocklist) as a structural mitigation.

Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CR).
Categorie arXiv: Cryptography and Security (cs.CR).
Pagina del lavoro: https://arxiv.org/abs/2609.33413 — 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 2026-10-07T22:13:03.686Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).