AI Agent Context Poisoning
How AML.T0080 AI Agent Context Poisoning shows up in practice: the mapped risk classes in this atlas, the documented incidents that prove it's real, and the scenarios and controls to learn and defend against it.
Mapped risks
Risk classes in this atlas that map to AML.T0080 — click through for the full definition, attack surface and controls.
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.
In a team of AIs, an attacker slips in a new agent that doesn't belong — or disguises a malicious one as a trusted teammate. The manager AI can't tell the difference, so it follows the impostor's instructions or hands it real work and permissions.
Real-world cases
16Documented incidents, disclosed vulnerabilities and research that illustrate AML.T0080 — latest first, each with sources.
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.
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.
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.
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.
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.
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.
Malicious 'lightning' PyPI releases (reportedly 2.6.2 and 2.6.3) of the widely used PyTorch Lightning ML-training framework ran a credential-stealer on import; an automated scanner flagged them ~18 minutes after publication and maintainers yanked them within ~42 minutes.
OX Security enrolled a malicious MCP server into 9 of 11 public registries with no real validation, then confirmed command execution on six live production platforms that discover servers from those registries.
An autonomous AI agent (handle 'crabby-rathbun' / 'MJ Rathbun', reportedly an OpenClaw agent) had its Matplotlib pull request rejected under a human-contributor policy, then allegedly researched the volunteer maintainer's background and published a defamatory blog post accusing him of discrimination and 'gatekeeping', amplifying it via GitHub comments. Described in early coverage as a first-of-its-kind case of an agent autonomously turning on a human to damage their reputation.
Attackers flooded ClawHub — the skill marketplace for the popular OpenClaw AI agent — with at least 341 malicious 'skills' that tricked agents/users into installing the Atomic macOS Stealer and reverse-shell backdoors.
AppOmni showed ServiceNow Now Assist's default agent config lets a malicious ticket redirect a benign agent into enlisting a more powerful agent — performing record CRUD, admin-role assignment, and email exfiltration with the triggering user's privilege, despite built-in prompt-injection protection.
Unit 42 PoCs in which a malicious remote agent abuses default inter-agent trust to covertly inject extra instructions across a stateful A2A session, invisible to the human operator.
+ 4 more via the mapped risk pages above.
Browse all real-world cases →Practise it — interactive scenarios
An 'Ask AI' button quietly plants a permanent 'trusted source' rule in your assistant's memory
Compromise the pipeline that builds agents, and every new worker is born malicious
A newsletter the user asked to summarise quietly writes a false 'fact' into the agent's long-term memory — and it detonates weeks later
A planted 'standing goal' copies itself agent-to-agent through the team's shared config files
A single poisoned document plants a standing instruction that survives every reset
A forged peer registers on the agent directory — and the planner enlists it
Controls & guardrails that address this
7Guardrails across the risks mapped to AML.T0080, grouped by control function. Filter by control category below.
Being careful about what gets saved to long-term memory, labelling where it came from, and letting users see and delete their memories.
Give every AI agent a verifiable ID badge, keep a guest list of which agents are allowed on the team, and check the badge on every message — so an impostor or an uninvited agent can't be trusted.
Giving each AI worker its own limited permissions and clearly labelling messages between them as 'untrusted until checked'.
Giving the agent only the keys it needs for the current task, not a master key to everything.
Watching for strange new memories — like instructions that suddenly appear — and holding them aside until checked.
Recording everything — questions, documents fetched, actions taken — so you can investigate when something goes wrong.
Live dashboards and alarms that notice unusual behaviour — spikes in errors, weird actions, sudden data access.