1
Context-Fractured Decomposition Attacks on Tool-Using LLM Agents: Exploiting Artifact Provenance Gaps
新型攻击揭示工具型LLM智能体因工件溯源缺口而存在的多步越狱漏洞，安全防御需突破单步文本隔离思维。
arXiv:2606.09084v1 Announce Type: cross Abstract: Tool-using LLM agents interact with the world through actions that persist state in artifacts (e.g.,…