Reproduce “A Blind Trust, the Bloody Thrust: When Attacker-Controlled Hook Updates Steer AI Agent Harnesses towards Malicious Behaviors” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Pengxun Li, Litian Zhang, Jianwei Hou, Shujiang Wu, Song Li, Zifeng Kang, Xi Zhang
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.