Compromise Is Not Consequence: Evaluating Task-Scoped Authorization in LLM Agents with Paired Replay
cs.CR
Submitted: 2026-10-05
Updated: 2026-10-05
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- LLM Agents Should Employ Security Principles
- SPA: Securing Persistent LLM Agents Across Queries with Plan-First Information-Flow 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