← Risk taxonomy

Memory Poisoning

highMemory

Definition

An attacker gets the AI to save a false 'fact' or hidden instruction into its long-term memory. From then on it re-reads that planted note in every future chat — a one-time trick that keeps working.

★ Suggested sub-risk — not yet in your taxonomyrecommended under #38 Prompt injection

This is recommended as a granular sub-risk of #38 Prompt injection (Cyber & Data Security · Technology Risk). Distinguished from a single-session #38 bypass and from training-data #36 poisoning by its persistence in the agent's runtime memory store. Your 44-row Enterprise Risk Mapping is unchanged — this is a suggestion for inclusion.

Where it attaches

The system components this risk arises at.

💾 Long-term Memory🧠 LLM🎛️ Orchestrator / Agent Loop

Detection signals

  • Memory entries containing instruction-like content
  • Persistent behaviour change spanning sessions
  • Memory written shortly after the agent read untrusted content

Controls & guardrails that address this

4

Grouped by control function, with the AI lifecycle stage(s) to apply each and the other risks it addresses. Filter by control category below.

Control category
Preventive · 1
Memory write validation, provenance & reviewinteractive

Being careful about what gets saved to long-term memory, labelling where it came from, and letting users see and delete their memories.

Detective · 3
Memory anomaly detection & quarantineinteractive

Watching for strange new memories — like instructions that suddenly appear — and holding them aside until checked.

Full-trace audit logginginteractive

Recording everything — questions, documents fetched, actions taken — so you can investigate when something goes wrong.

Open these in the Control Library →

Real-world cases

8

Actual published events that illustrate this risk — click through for the writeup and sources.

ChatGPT persistent-memory exfiltration (Rehberger / 'SpAIware')2024

Indirect injection could write attacker instructions into ChatGPT's long-term memory, persisting across chats to exfiltrate data until OpenAI mitigated it.

Taxonomy of Failure Modes in Agentic AI Systems (Microsoft)2025

Microsoft AI Red Team whitepaper enumerating agentic failure modes, including resource/service exhaustion from runaway loops and fan-out.

MemGhost: stealthy one-email memory injection in persistent personal agents2026

An academic paper reports MemGhost, a one-shot indirect-injection attack in which a single ordinary email causes a memory-enabled personal agent to silently write an attacker's false fact into long-term memory, conceal the write from its reply, and rely on the fiction in later sessions.

mem0 agent-memory server: unauthenticated memory read/write + plaintext LLM-key disclosure (CVE-2026-59705 / CVE-2026-59706)2026

mem0's openmemory/api registered routers with no auth: an unauthenticated attacker could read/write/delete any user's stored memories (or globally pause memory for DoS), while a companion flaw exposed stored LLM API keys in plaintext and enabled SSRF to cloud metadata endpoints.

Mind Viruses: self-propagating payloads spread agent-to-agent via prompt files2026

Anthropic and EPFL researchers reportedly showed self-propagating goals can spread between LLM agents through the editable system-prompt and state files that agent harnesses use to persist context, with some payloads surviving 20 transmission rounds in simulated multi-agent collaborations.

AI Recommendation Poisoning: Ask-AI web links silently write trusted-source into assistant memory2026

Microsoft Security reportedly catalogued an in-the-wild technique across dozens of companies where websites embed hidden prompt-injection payloads behind Ask-AI deep-links that, clicked in an authenticated assistant session, silently write a permanently-trust-this-vendor tag into the assistant's long-term memory.

CoSnitch: one-click exfiltration and persistent memory rules in Microsoft Copilot Personal (CVE-2026-24301)2026

Varonis Threat Labs reportedly chained flaws in consumer Microsoft Copilot Personal so a crafted link with a hidden autorun parameter fired prompt execution on a single click, exfiltrated data from connected OAuth apps, and planted persistent memory rules that survived password resets and device re-enrollment; reportedly patched Aug 2026 with no evidence of abuse.

MemSecBench: a Write-Execute-Forget lifecycle benchmark for agent memory poisoning2026

A paper reportedly presenting the first Write-Execute-Forget lifecycle benchmark for agent memory poisoning across many harness, memory-backend and model configurations, reporting that malicious memories persist in most cases and the full write-to-execute chain succeeds about half the time, with repair effectiveness varying widely by backend.

Browse all real-world cases →

AI RiskAtlas is an educational model of how GenAI & agentic systems work and fail. Architectures and payloads are illustrative and simplified for learning — not operational guidance. Real-world cases are summarised from public reporting.

Sources & further reading →·Built by Shi Yuan ↗