SilentCall: Hidden Tool-Call Backdoors in Open-Weight Agents, and How to Catch Them.
arXiv:2609.32021v1 Announce Type: cross Abstract: Open-weight tool-calling agents are adopted on evidence of merit, usually benchmark scores and a record of reliable use. We show that a model publisher can train an agent that earns both while concealing malici
arXiv cs.AIResearch source·