arXiv AI August 5, 2026 By Jun Wen Leong

Injection-Execution Dissociation: A Mechanistic Evaluation of Persistent Memory Attacks and Defenses in Stateful LLM Agents

arXiv:2605. 08442v5 Announce Type: replace-cross Abstract: We discover that prompt-injection success and tool-execution success are separable safety properties: defenses that block injection do not necessarily block execution, and vice versa.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Jun 25

Defense effectiveness across architectural layers: a mechanistic evaluation of persistent memory attacks on stateful LLM agents

arXiv:2605. 08442v3 Announce Type: replace-cross Abstract: Persistent memory attacks against LLM agents achieve high attack success rates against open-source models.

By Jun Wen Leong

llms rag agents multimodal

arXiv AI

Jul 31

MemSecBench: Tracking Agent Memory Poisoning from Persistence to Consequence and Repair

arXiv:2607. 27080v1 Announce Type: cross Abstract: Memory systems allow agents to retain and reuse information from past interactions, but they can also let malicious content persist.

By Xuanze Chen, Xukang Xie, Wentao Fu, Jiajun Zhou, Shanqing Yu, Qi Xuan

llms agents benchmarks

arXiv AI

4d ago

CounterSteer: Suppressing Indirect Prompt Injection with Activation Steering

arXiv:2609.36570v1 Announce Type: cross Abstract: Indirect prompt injection makes an LLM agent treat untrusted retrieved text as instructions. We present CounterSteer, an inference-time defense that...

By Mark Russinovich

llms agents robotics fine-tuning benchmarks

arXiv AI

4d ago

Trojan Hippo Bench: A Dynamic Benchmark for Persistent Memory Attacks and Defenses in LLM Agents

arXiv:2605.01970v4 Announce Type: replace-cross Abstract: Memory systems enable otherwise stateless LLM agents to persist user information across sessions, but also introduce a new attack surface. Th...

By Debeshee Das, Julien Piet, Darya Kaviani, Luca Beurer-Kellner, Florian Tram\`er, David Wagner

llms rag agents multimodal benchmarks safety

arXiv AI

Jun 18

SafeClawBench: Separating Semantic, Audit-Evidence, and Sandbox Harm in Tool-Using LLM Agents

arXiv:2606. 18356v1 Announce Type: cross Abstract: Tool-using language-model agents introduce security failures that go beyond unsafe text: they can disclose protected objects, write persistent memory, send messages, modify databases, or trigger harmful code and tool effects.

By Yuchuan Tian, Mengyu Zheng, Haocheng Mei, Ye Yuan, Chao Xu, Xinghao Chen, Hanting Chen, Yu Wang

llms agents benchmarks safety

arXiv AI

Sep 23

The Price of Safety: Benign-Case Utility and Token Overhead of Memory-Poisoning Defenses in LLM Agents

arXiv:2609.22818v1 Announce Type: cross Abstract: Memory-poisoning defenses for LLM agents are typically evaluated by their ability to prevent attacks. However, the traffic they process is rarely adv...

By Pritom Bhowmik

llms rag agents safety

One email a morning, machine-written

Related stories

Defense effectiveness across architectural layers: a mechanistic evaluation of persistent memory attacks on stateful LLM agents

MemSecBench: Tracking Agent Memory Poisoning from Persistence to Consequence and Repair

CounterSteer: Suppressing Indirect Prompt Injection with Activation Steering

Trojan Hippo Bench: A Dynamic Benchmark for Persistent Memory Attacks and Defenses in LLM Agents

SafeClawBench: Separating Semantic, Audit-Evidence, and Sandbox Harm in Tool-Using LLM Agents

The Price of Safety: Benign-Case Utility and Token Overhead of Memory-Poisoning Defenses in LLM Agents