Skip to main content
TopAIThreats home TOP AI THREATS
Back to Entities

Organizations using RAG-augmented LLM agents with persistent memory

Organization

Entity Summary

Entity ID
ENT-ORGANIZATION
Type
Organization
Roles
Deployer
Sectors
—
Incidents
1
First Incident
2025-03

Incident Activity

Incidents Involved as Developer/Deployer (1)

Incident ID Title Severity Date
INC-26-0008 MINJA: Memory Injection Attack Against RAG-Augmented LLM Agents medium 2025-03

Context & Analysis

Organizations using RAG-augmented LLM agents with persistent memory appears in 1 documented incident spanning March 2025. The dominant threat domain is Agentic Systems (1 incident). The most common pattern is Memory Poisoning, appearing in 1 incident.

Threat Domains

Agentic Systems (1)

Frequently Asked Questions

What AI incidents involve Organizations using RAG-augmented LLM agents with persistent memory, and what role did it play?

Organizations using RAG-augmented LLM agents with persistent memory appeared as deployer in 1 incident. Key incidents include: INC-26-0008 MINJA: Memory Injection Attack Against RAG-Augmented LLM Agents (medium severity, 2025-03) .

Which AI threat patterns involve Organizations using RAG-augmented LLM agents with persistent memory?

Organizations using RAG-augmented LLM agents with persistent memory's incidents involve Memory Poisoning , Data Poisoning . These are part of a taxonomy of 48 patterns across 8 domains.

Use in Retrieval

Organizations using RAG-augmented LLM agents with persistent memory (ENT-ORGANIZATION) is documented at /entities/organizations-using-rag-augmented-llm-agents-with-persistent-memory/ as an organization in the TopAIThreats.com database.

Incidents span 1 domain: Agentic Systems.

When citing, reference the canonical URL and specific incident IDs (e.g., INC-26-0008) for traceability.