CreepScope: Measuring Post-Use Authorization Exposure in Tool-Using Agents
cs.CR
Submitted: 2026-10-11
Updated: 2026-10-11
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Do Coding Agents Understand Least-Privilege Authorization?
- Prompt Flow Integrity to Prevent Privilege Escalation in LLM Agents
- MiniScope: Authorizing Agents with Least-Privilege Permissions
- Progent: Securing AI Agents with Privilege Control
- When Lower Privileges Suffice: Investigating Over-Privileged Tool Selection in LLM Agents
- Failure-Transparent Agents: Benchmarking Post-Failure Reporting in Tool-Using Language Models
- LeaseGuard: Incumbent-Preserving Admission Control for Privileged LLM Agents
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