Names Are Not Objects: Object-Bound Confinement for Compromised AI Coding Agents
cs.CR
Submitted: 2026-10-10
Updated: 2026-10-10
Code: https://github.com/github/copilot-cli
Sources
- Design Patterns for Securing LLM Agents against Prompt Injections
- Systems Security Foundations for Agentic Computing
- Securing AI Agents with Information-Flow Control
- Defeating Prompt Injections by Design
- Defending Against Indirect Prompt Injection Attacks With Spotlighting
- Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
- Taming Various Privilege Escalation in LLM-Based Agent Systems: A Mandatory Access Control Framework
- Mind the Gap: Time-of-Check to Time-of-Use Vulnerabilities in LLM-Enabled Agents
- The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections
- The Balkanization of Execution-Security Research for AI Coding Agents: Isolation, Access Control, and Time-of-Check-to-Time-of-Use Vulnerabilities
- Lingering Authority: Revocable Resource-and-Effect Capabilities for Coding Agents
- AC4A: Access Control for Agents
- Progent: Securing AI Agents with Privilege Control
- An AI Agent Execution Environment to Safeguard User Data
- The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions
- Sandlock: Confining AI Agent Code with Unprivileged Linux Primitives
- AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents
- Aligning Provenance with Authorization: A Dual-Graph Defense for LLM Agents
- Approval Laundering: Systematizing Approval--Execution Binding Failures in AI Coding-Agent Harnesses
- Agent libOS: A Runtime Substrate for Capability-Controlled Self-Evolving 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