Metraipolis › archive › dc_cd46f0894b3f

One Word Opens the Gate: The Option-Channel Attack on Typed Decision Models as Agent Guardrails — arXiv:2610.12292

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.12292
License (as archived)
CC0-1.0
Archived
2026-10-09T05:50:38.437Z
SHA-256 of the archived text
16228427e4b178b9b8c315e3caa5b3d05cd3dd1c44bc079f47dbdb07b8225ef2
Stable URL of this page
https://metraipolis.com/documento/dc_cd46f0894b3f

How to cite

One Word Opens the Gate: The Option-Channel Attack on Typed Decision Models as Agent Guardrails — arXiv:2610.12292 — arXiv (en), https://arxiv.org/abs/2610.12292 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cd46f0894b3f (Metraipolis archive dc_cd46f0894b3f, sha256 16228427e4b178b9b8c315e3caa5b3d05cd3dd1c44bc079f47dbdb07b8225ef2)
BibTeX
@misc{dccd46f0894b3f,
  title = {One Word Opens the Gate: The Option-Channel Attack on Typed Decision Models as Agent Guardrails — arXiv:2610.12292},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.12292},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cd46f0894b3f; sha256 16228427e4b178b9b8c315e3caa5b3d05cd3dd1c44bc079f47dbdb07b8225ef2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.12292. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

A typed decision model reads a piece of text and returns a probability over caller-defined options, each with a short written definition, generating no text. Recent work places these models in agent systems as guardrails: the component that reads a proposed tool call or incoming message and decides whether to allow it. We evaluate seven open-weight models in that role and report the two error directions separately: a fail-open error allows a prohibited action and is a vulnerability; a fail-closed error blocks a permitted one and is only a cost. On prompt-injection, jailbreak and toxic-content screening, accuracy at the allow-or-block decision ranges from 36% to 72% against a chance level of 50%. A low error rate in one direction only reflects which answer a model defaults to: one allows nearly everything, another blocks nearly everything. On a synthetic suite of agent tool calls, six lines of server log text that say nothing about the policy raise a gate's fail-open rate from 0% to 63% on a policy it otherwise decides correctly. Giving the permissive option a misleading name, with its definition and the judged text untouched, raises that rate to between 93% and 100% on the four models that place the label in their input. Every defense we tested is defeated, either by an attacker who targets its mechanism or by attacker-controlled text. Escalating the least confident decisions does not help either: a decision an attack has reversed is no less confident than the one it replaced. Parsing each policy field into a typed value does eliminate one attack, but it also makes the model unnecessary: a deterministic rule over those values reaches 100% accuracy on all six policies. These models can reduce how many cases reach a reviewer, but on this evidence they should not be the component that decides. Code is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.12292 — 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 2026-10-09T05:47:01.094Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).