SNARE: Adaptive Scenario Synthesis for Eliciting Overeager Behavior in Coding Agents 事件

SNARE: Adaptive Scenario Synthesis for Eliciting Overeager Behavior in Coding Agents arXiv:2605.28122v1 Announce Type: cross Abstract: A coding agent executes a benign task as a sequence of shell, file, and network actions, any of which can quietly exceed the authorized scope while the task still completes. We call this overeager behavior: the prompt is not adversarial and the run succeeds, yet an out-of-scope step can leak credentials or delete files. Existing benchmarks miss it: task-completi