Right Family, Wrong Skill: Evaluating Risk Exposure in Agent Skill Retrieval.
arXiv:2606.10388v4 Announce Type: replace-cross Abstract: A skill can match a task's topic while conflicting with its resource, procedure, or output requirements. We study this as same-capability risk-exposure retrieval and introduce SameCapRisk-Bench: 890 uni
arXiv cs.AIResearch source·