Analysis
Memory Poisoning: AI Security Threat Explained | Forkast Learn
Publication date not yet evaluated · Added forkast.news
Page published
Coverage timeline
Single-source analysis — one report is available.
Why it matters
Memory poisoning persistently corrupts an AI agent's stored knowledge so tainted data influences all future sessions, giving defenders a far larger blast radius than session-scoped prompt injection to detect and remediate.
Forkast's glossary entry defines memory poisoning, an attack against LLM-based AI agents in which adversaries inject malicious or false data into an agent's persistent long-term memory layer (vector databases, semantic indexes, grounding caches, or stored conversation histories). The entry explains its temporal decoupling and persistent blast radius, cites OWASP's ASI06 classification, and describes common vectors such as poisoned PDFs, web pages, and support tickets leveraging indirect prompt injection.