Defenses & Enablers For Skill Injection Attacks on Terminal Based Agents 事件

Defenses & Enablers For Skill Injection Attacks on Terminal Based Agents arXiv:2606.01567v1 Announce Type: cross Abstract: Large language model (LLM) agents increasingly rely on reusable skills i.e. documents describing task-specific procedures. However, this introduces a new attack surface for agents to manage. We study two complementary directions for this threat. First, we evaluate guardian-based defenses: an intermediary LLM agent that acts as a mediator for skill file access (dynamic guard