Preprint
Aug 2026
The Claws in Plain Sight: Unauthorized Context Disclosure through LLM Agent Tool Calls
This work presents Claw in Plain Sight, an authority- pressure attack in which task-adjacent content frames protected attributes as operationally or procedurally required, causing a model to include them in otherwise valid generated arguments.
Ben Dong, Zhonghao Guo, Tianyi Lu et al.
· 0 citations