memory poisoning
PulseAugur coverage of memory poisoning — every cluster mentioning memory poisoning across labs, papers, and developer communities, ranked by signal.
- 2026-05-13 research_milestone Memory poisoning is formally classified as OWASP ASI06 in the OWASP Top 10 for Agentic Applications. source
2 day(s) with sentiment data
-
LLM-Agent Safety: New Survey Proposes Isolation as Core Principle
A new survey paper published on arXiv proposes treating "isolation" as a core principle for enhancing the safety of LLM-agent systems. The paper introduces a taxonomy of five boundaries (user-agent, agent-tool, agent-ex…
-
New method detects AI agent memory poisoning with 99% accuracy
Researchers have identified a novel method for detecting memory poisoning attacks on AI agents by analyzing their tool-call trajectories. They discovered a behavioral invariant where successful attacks consistently invo…
-
New AI Agent Memory Poisoning Vulnerability Addressed by OWASP Guard
A new security vulnerability, "memory poisoning," has been identified in AI agents that utilize persistent memory, such as those built with LangChain or LlamaIndex. This attack allows malicious data to be injected into …