Community news / T SALON

EDITORIAL

Memory Poisoning: Long-Term Memory Controls for Agents

If a system records a fake contact as a trusted supplier, the impact extends beyond the current conversation. Memory Poisoning is a critical risk for AI Agents.

Memory Poisoning
T SALON / COMMUNITY ARCHIVE

This article explains the details originally posted on SegmentFault.

(Full English translation pending)

TOPICS
AIAgentSecurity