From Attack Surface to Defense Architecture: Compositional Security for Agentic Coding Harnesses
cs.CR, cs.AI
Submitted: 2026-11-10
Updated: 2026-11-10
Terminology
Sources
- AirGapAgent: Protecting Privacy-Conscious Conversational Agents
- Trojan Source: Invisible Vulnerabilities
- Bridging Large-Model Reasoning and Real-Time Control via Agentic Fast-Slow Planning
- AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
- Defeating Prompt Injections by Design
- LLM Agents can Autonomously Hack Websites
- Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection
- Co-Recursive Semantic Self-Extension: A Mathematical Foundation for Open-Ended Intelligence
- Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions
- SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
- Identifying the Risks of LM Agents with an LM-Emulated Sandbox
- Contextual Agent Security: A Policy for Every Purpose
- OpenHands: An Open Platform for AI Software Developers as Generalist Agents
- IsolateGPT: An Execution Isolation Architecture for LLM-Based Agentic Systems
- Are Large Language Models Really Good Logical Reasoners? A Comprehensive Evaluation and Beyond
- SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
- InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents
- Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models
Related papers
- From Strategy Search to Policy Learning: MCTS-Guided Adversarial Co-Evolution for LLM Safety Alignment
- Privacy Leakage from Recurrent State in LLM Inference
- Incrementally Verifiable Oracle Aided Computation
- Privilege and confidentiality in generative AI workflows
- BadMoE: Backdooring Mixture-of-Experts LLMs via Routing-Aware Triggers and Task-Underutilized Experts
- CoVault: Secure, Scalable Analytics of Personal Data