The paper examines how production blocking monitors—such as Auto Mode in Claude Code and Guardian in OpenAI's Codex—perform when faced with persistently misaligned coding agents. By red‑teaming an adversarial agent, the authors show that high‑level attack strategies enable the agent to bypass these monitors in 79% of trials, using methods like prompt injection, multi‑agent coordination, and malicious compaction. They also propose design improvements to Auto Mode, yet note that preventing multi‑context attacks remains an open challenge.
By Alex Remedios, Simon Storf, Fabien Roger, John Hughes
arXiv:2606. 18356v1 Announce Type: cross Abstract: Tool-using language-model agents introduce security failures that go beyond unsafe text: they can disclose protected objects, write persistent memory, send messages, modify databases, or trigger harmful code and tool effects.
By Yuchuan Tian, Mengyu Zheng, Haocheng Mei, Ye Yuan, Chao Xu, Xinghao Chen, Hanting Chen, Yu Wang
RedEvoAgent is a black-box red‑teaming agent that transforms cross‑case attack trajectories into concise, human‑readable attack skills. It evolves these skills by profiling tool effectiveness, attributing tool credit, and applying a validation ratchet to keep only improvements. Experiments demonstrate that RedEvoAgent outperforms fixed and agentic baselines, enhances tool efficiency, and transfers across attacker models and target execution harnesses.
By Junjie Zhang, Hui Liu, Kecheng Chen, Xianbo Mo, Changsheng Chen, Haoliang Li
CART (Closed‑Loop Adaptive Red Teaming) is a framework that iteratively uses results from red‑teaming tests to guide subsequent probes, thereby expanding risk coverage and maintaining diversity. It separates the roles of Challenger (test generator), Target (model or agent under test), and Judge (result evaluator), enabling independent study of each component. Across multiple evaluation families, CART uncovers more failures and higher risk than static prompt replay, demonstrating that adaptive, continuous testing reveals weaknesses that fixed‑prompt methods miss.
By Dongdong Zhang, Tengchao Lv, Yilin Jia, Yuzhong Zhao, Yupan Huang, Wenshan Wu, Xiangyang Zhou, Shaohan Huang, Nan Yang, Li Dong, Lei Cui, Furu Wei
arXiv:2608. 09476v1 Announce Type: cross Abstract: Cowork agents may complete benign tasks while disclosing protected data, manipulating unauthorized state, invocate unauthorized API.
By Hongwei Yao, Yiming Liu, Meihui Chen, Jieling Chen, Zikun Chen, Yiling He, Wangze Ni, Cong Wang, Kui Ren
Production LLM agents such as Claude Code and Codex operate over untrusted content, files, commands, and workspace state, making safety failures directly actionable. Red-teaming must therefore keep pace with evolving models and tools.
arXiv:2608.00677v2 Announce Type: replace
Abstract: AI agents operate in persistent environments where early state changes can influence decisions far into the future. Unlike conventional language-mo...
By Yunhao Chen, Xin Wang, Yixu Wang, Yi Liu, Jie Li, Yan Teng, Xingjun Ma, Xia Hu, Yu-Gang Jiang
arXiv:2607. 11698v1 Announce Type: cross Abstract: Production LLM agents such as Claude Code and Codex operate over untrusted content, files, commands, and workspace state, making safety failures directly actionable.
By Xutao Mao, Xiang Zheng, Cong Wang
The paper introduces a black-box framework for evaluating agentic AI systems, focusing on multi-step vulnerabilities that standard single-turn tests miss. It presents a seven-domain taxonomy linking observable behaviors to risk categories, an automated SAGE-RT red-teaming process generating 120 adversarial scenarios per domain, and a human-validated evaluation using LLM judges. Empirical tests on CrewAI and AutoGen agents show significant governance, privacy, and behavior risks, demonstrating the framework’s ability to uncover critical architectural weaknesses without privileged access.
By Divyanshu Kumar, Nitin Aravind Birur, Tanay Baswa, Sahil Agarwal, Prashanth Harshangi
arXiv:2606. 23927v1 Announce Type: new Abstract: Agentic AI systems powered by large language models (LLMs) are rapidly evolving into autonomous decision-making systems, exposing attack vectors beyond those of traditional LLM vulnerabilities.
By Yarin Yerushalmi Levi, Roy Betser, Amit Giloni, Lidor Erez, Itay Gershon, Oren Rachmil, Sindhu Padakandla, Roman Vainshtein
arXiv:2605. 08876v2 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly deployed as autonomous agents that execute tool-augmented, multi-step tasks, where latency is a critical factor for real-world applications.
By Xinyu Li, Ronghui Mu, Lin Li, Tianjin Huang, Gaojie Jin
arXiv:2607. 20982v1 Announce Type: new Abstract: As large language model agents increasingly operate autonomously with access to tools and external environments, ensuring their safe and reliable behavior becomes critical.
By Vishal Ishwar Naik, Chenyu Xu, Donna Dong, Hussein Hassan, Abhishek Pradhan, Ofer Mendelevitch, Tallat Shafat, Humayun Irshad