arXiv CS
open access
One Word Opens the Gate: The Option-Channel Attack on Typed Decision Models as Agent Guardrails
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
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- One Word Opens the Gate: The Option-Channel Attack on Typed Decision Models as Agent Guardrails#1249716
- Typed Decision Models: An Early Evidence Audit and Evaluation Checklist#1116491
- LEASH: Uncertainty-Aware Weak-to-Strong Escalation and Oversight for Computer-Use Agents#1357935
- LEASH: Uncertainty-Aware Weak-to-Strong Escalation and Oversight for Computer-Use Agents#1348892
- Control-Token Injection Suppresses Chain-of-Thought and Defeats Reasoning-Based Oversight in Tool-Using Agents#1064086
Record · ID 1242794
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive