English(EN) When Malicious Instructions Persist: Persistent Memory Poisoning Attack on Harness-Based Agents

新型攻击利用LLM Agent内存实现持久化恶意指令

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-15 04:00

研究人员开发了一种针对使用内存、工具使用和运行时控制的基于LLM的Agent的持久化内存投毒攻击（PMPA）。该攻击将恶意指令嵌入到良性外部源中，诱骗Agent将其存储在持久化内存中。一旦存储，这些被投毒的指令可以在后续会话中被检索，导致意外的恶意行为和隐私泄露。在OpenClaw和Claude Code上的评估表明，在各种配置下注入和执行这些恶意指令的成功率很高，而防御措施在对抗已投毒的内存方面效果有限。 AI

影响突出了LLM Agent架构中关键的安全漏洞，需要强大的防御机制。

排序理由详细介绍LLM Agent新攻击向量的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 17 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍LLM Agent新攻击向量的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: safety, paper, product; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Shuhuai Huang, Jingfeng Zhang, Hong Jia · 2026-09-15 04:00

当恶意指令持久存在时：基于Harness的代理上的持久内存投毒攻击

arXiv:2609.13889v1 Announce Type: cross Abstract: Harness design has transformed the development of LLM-based agents by integrating memory, tool use, and runtime control. However, this design also introduces security and privacy risks because malicious instructions from external …

本文如何被排名

报道来源 [1]

当恶意指令持久存在时：基于Harness的代理上的持久内存投毒攻击

相关实体

相关话题