The Vulnerability With No CVE: Managing Persistent Gaps Between Mandate and Authority in AI Coding Agents

arXiv:2608.05884 · cs.CR, cs.CL · Submitted 2026-08-06 · Read on arXiv

Shayell Aharon Salomon Amir Shaked Matan Noga

cs.CR, cs.CL

Submitted: 2026-08-06

Code: https://github.com/zed-industries/zed

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Composition — 8× in this paper · explained in 2 episodes
• AI Agents — 6× in this paper · explained in 2 episodes
• Abstraction — 2× in this paper · explained in 1 episode
• Agent Harness — 1× in this paper · explained in 2 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Harness — 1× in this paper · explained in 2 episodes
• Planner — 1× in this paper · explained in 3 episodes
• Provenance — 1× in this paper · explained in 5 episodes

Sources

• Runtime Governance for AI Agents: Policies on Paths
• When Developer Aid Becomes Security Debt: A Systematic Analysis of Insecure Behaviors in LLM Coding Agents
• Overeager Coding Agents: Measuring Out-of-Scope Actions on Benign Tasks
• Beyond OAuth: Task-Scoped Authorization for AI Agents via Natural Language Slices
• Authenticated Delegation and Authorized AI Agents
• Before the Tool Call: Deterministic Pre-Action Authorization for Autonomous AI Agents
• AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents
• The Authorization-Execution Gap Is a Major Safety and Security Problem in Open-World Agents
• Do Coding Agents Understand Least-Privilege Authorization?
• Intent-Governed Tool Authorization for AI 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
• Estimating the Social Cost of Corporate Data Breaches
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills