What a Policy Gate Can and Cannot Know: Measured Boundaries of Cross-Platform Command Adjudication
cs.CR
Submitted: 2026-10-04
Updated: 2026-10-04
Comments: 13 pages, 8 figures, 6 tables. Supplementary material and reproducibility artifact are included as ancillary files
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Separation of Duties for Privileged LLM Agents: A Governed Execution Architecture with Measured Security-Utility Trade-offs
- Design Patterns for Securing LLM Agents against Prompt Injections
- Progent: Securing AI Agents with Privilege Control
Related papers
- SoK: AI-Augmented Binary Reversing
- Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
- Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
- Efficient Fuzzy PSI under One-Sided Assumptions
- Sealing the Audit-Runtime Gap for LLM Skills
- Token Composition: A Graph Based on EVM Logs