Do User-Authored Permission Policies Improve Protection Against AI Agent Overreach?
cs.HC, cs.CR
Submitted: 2026-08-27
Updated: 2026-08-27
Terminology
Sources
- Janus: a Playground for User-Involved Agentic Permission Management
- Measuring the Permission Gate: A Stress-Test Evaluation of Claude Code's Auto Mode
- Options, Not Clicks: Lattice Refinement for Consent-Driven MCP Authorization
- How Agents Ask for Permission: User Permissions for AI Agents, from Interfaces to Enforcement
- Automated Annotation with Generative AI Requires Validation
- SoK: Trust-Authorization Mismatch in LLM Agent Interactions
- Progent: Securing AI Agents with Privilege Control
- Oversight Has a Capacity: Calibrating Agent Guards to a Subjective, Fatiguing Human
- Reframing LLM Agent Security as an Agent-Human Interaction Problem
- SkillScope: Toward Fine-Grained Least-Privilege Enforcement for Agent Skills
- MiniScope: Authorizing Agents with Least-Privilege Permissions
Related papers
- EduGage: A Multimodal Dataset and Benchmark for Sensor-Based Momentary Assessment of Engagement in Self-Guided Video Learning
- EvoDesign: Agentic Editable Diagram Creation via Design Expertise Evolution
- HAGI++: Head-Assisted Gaze Imputation and Generation
- Linking Behaviour and Perception to Evaluate Meaningful Human Control over Partially Automated Driving
- Review of Explainable Decision Support and Adaptive Human-Machine Interfaces for Automation Transparency in Maritime Autonomous Surface Ships
- Towards Cognitive Process-Aware Proactive Writing Support