When the Approved File Is Unchanged: Authority-Set Integrity for Deployment and Coding-Agent Approvals
cs.CR, cs.SE
Submitted: 2026-10-10
Updated: 2026-10-10
Code: https://github.com/cursor/cursor
Sources
- Separation of Duties for Privileged LLM Agents: A Governed Execution Architecture with Measured Security-Utility Trade-offs
- Loopjacking: Hijacking Human-in-the-Loop Approval
- Mind the Gap: Time-of-Check to Time-of-Use Vulnerabilities in LLM-Enabled Agents
- The Balkanization of Execution-Security Research for AI Coding Agents: Isolation, Access Control, and Time-of-Check-to-Time-of-Use Vulnerabilities
- Demystifying and Detecting Agentic Workflow Injection Vulnerabilities in GitHub Actions
- Approval Laundering: Systematizing Approval--Execution Binding Failures in AI Coding-Agent Harnesses
- What You Approve Is What Executes: Consent Integrity for Black-Box LLM Agents
- The Authorization-Execution Gap Is a Major Safety and Security Problem in Open-World Agents
- Agent Approval Laundering: Transitive Effects Beyond the Approved Invocation
- CATP: Design and Evaluation of Local Agent Authorization and Audit Evidence
- Versioned Transitive Dependency-Closure Binding and Operation-Time Effect Governance for Agent Skills: ClosureBound
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