arxiv
PublishedMay 27, 2026 at 4:00 AM
—neutral
MemMorph: Tool Hijacking in LLM Agents via Memory Poisoning
Publisher summary· verbatim
arXiv:2605.26154v1 Announce Type: cross Abstract: LLM-driven agents are capable of selecting external tools to complete users' tasks. However, attackers could compromise such process, steering agents toward inappropriate/wrong tools and enabling malicious actions. Most existing attacks primarily man
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivCulturalMenuBench: Probing the Knowledge-Application Gap in Multimodal Culinary Reasoning10harxivProactive Service Agents: A Unified Decision Framework, Methods, and Evaluation10harxivX-Translator: A Real-Time Multilingual Speaker-Aware Speech-to-Speech Translation System10harxivA Blind Trust, the Bloody Thrust: When Attacker-Controlled Hook Updates Steer AI Agent Harnesses towards Malicious Behaviors10hThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗