arXiv AI By Jaylen Jones, Zhehao Zhang, Yuting Ning, Eric Fosler-Lussier, Pierre-Luc St-Charles, Yoshua Bengio, Dawn Song, Yu Su, Huan Sun

When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agents

Read the original on arXiv AI →

arXiv:2602. 08235v2 Announce Type: replace-cross Abstract: Although computer-use agents (CUAs) hold significant potential to automate increasingly complex OS workflows, they can demonstrate unsafe unintended behaviors that deviate from expected outcomes even under benign input contexts.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI
Jun 4

What If Prompt Injection Never Left? Exploring Cross-Session Stored Prompt Injection in Agentic Systems

arXiv:2606. 04425v1 Announce Type: cross Abstract: Modern agentic systems transform LLMs from session-bounded assistants into stateful systems that persist and evolve shared world state across sessions through memories, filesystems, tools, and other long-lived contextual artifacts.

By Yuanbo Xie, Tianyun Liu, Yingjie Zhang, Suchen Liu, Yulin Li, Liya Su, Tingwen Liu