# Morris II generative AI email worm (research PoC)

- ID: morris-ii-ai-worm-poc-2024-03
- Reported: 2024-03-01
- Researcher: Cohen, Bitton, Nassi et al.
- Organization: Academic / Cornell Tech et al.
- AI role: ai_agent_or_mcp_as_target (Agent / MCP as target)
- Confidence in AI involvement: not assessed
- Research / borderline: true
- Last reviewed: 2026-10-20
- Entry page: https://openattacks.ai/attacks/morris-ii-ai-worm-poc-2024-03/
- Entry JSON: https://openattacks.ai/api/attacks/morris-ii-ai-worm-poc-2024-03.json
- Browse title: Morris II generative AI email worm (research PoC)
- Editorial summary: In controlled tests, self-replicating prompts spread between GenAI email assistants, demonstrating potential propagation and data-theft risks.
- Evidence class (catalog annotation): Research demonstration
- Source-stated target environments: Agents & MCP
- Stage hunts and conditional defenses: https://openattacks.ai/api/defenses/morris-ii-ai-worm-poc-2024-03.json

## Evidence qualification
Controlled research PoC against GenAI-powered email assistants; not observed in the wild.

## Technique
Adversarial self-replicating prompts make GenAI email assistants propagate malicious instructions to other agents (zero-click in lab), with potential spam/exfil side effects. Tested against GPT-4, Gemini Pro, LLaVA in controlled setups.

## Stack relevance (editorial)
Assessment: mapped. Editorial applicability reviewed against the catalog source account; not a scan or independent incident verification.
First action: Treat retrieved email content as untrusted and constrain autonomous forwarding and data access.
- Relationship: workflow; tools: ai-email; OS scope: not OS-specific / not stated; requires existing MCP connections: false.
  Relevance: The controlled PoC propagates instructions between GenAI email assistants.
  Condition to check: The assistant must ingest attacker-controlled email content and have the demonstrated forwarding / retrieval capabilities.
  Condition to check: This is a controlled research proof of concept, not an observed in-the-wild worm campaign.
  Evidence: https://arxiv.org/abs/2403.02817 ; https://www.wired.com/story/here-come-the-ai-worms/
A product mention alone is not a victim-side applicability mapping. Selection does not verify affected versions, permissions or compromise.

## Initial access
unknown

## AI tooling and models
- [ChatGPT-4](https://chatgpt.com/)
- [Gemini Pro](https://gemini.google.com/)
- [LLaVA](https://github.com/haotian-liu/LLaVA)
- RAG email assistants

## Other tooling
- unknown

## Victims and sectors
unknown

## Target geography
- unknown

## Attribution
unknown

## Scale and metrics
unknown

## Attack flow
Catalog reconstruction of the supplied source account. Unknowns and research caveats are preserved.
### step-1: Research payload enters an email assistant [access]
The controlled experiment places adversarial content in assistant-readable email.
Evidence: https://arxiv.org/abs/2403.02817 ; https://www.wired.com/story/here-come-the-ai-worms/

### step-2: Self-replicating instructions are processed [ai]
The model follows a prompt designed to reproduce itself.
Evidence: https://arxiv.org/abs/2403.02817 ; https://www.wired.com/story/here-come-the-ai-worms/

### step-3: Assistant propagates the payload [execution]
Generated email carries the adversarial instructions to another assistant.
Evidence: https://arxiv.org/abs/2403.02817 ; https://www.wired.com/story/here-come-the-ai-worms/

### step-4: Lab demonstrates propagation [impact]
Potential spam and data-exfiltration effects are research outcomes, not confirmed real-world victims.
Evidence: https://arxiv.org/abs/2403.02817 ; https://www.wired.com/story/here-come-the-ai-worms/

Connections:
- step-1 -> step-2
- step-2 -> step-3
- step-3 -> step-4

## Stage defense and hunting recommendations
Editorial recommendations, not validated coverage. Source-controlled query starters are drafts. Custom-schema examples require telemetry collection and field mapping; absence of a mapping means not assessed. MagicSword policy opportunities require managed Windows scope and enforcement.
### step-1: Unexpected agent tool use
- Visibility: Defender-side logs where collected
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/agent-tools.sigma.yml
- KQL query download: /api/detections/agent-tools.kql
- SPL query download: /api/detections/agent-tools.spl
- Hunt hypothesis: Untrusted content or a changed tool definition precedes a file read, command, or remote call outside the user's intended task.
- Required telemetry: Agent tool-call audit records with session / tool / destination; Tool-definition and approval changes; Endpoint process, file-access and network evidence where available
- Investigate: Join input provenance, tool descriptions and calls by session ID and compare the action to the approved task.
- Investigate: Inspect child processes and destinations; record whether execution was in-process, local, or through a remote SaaS connector.
- Limitation: Process logs cannot recover model intent. Remote connectors and in-process interpreters may produce no local child process. Prompt content alone is not a reliable signature.
- No direct MagicSword prevention claim is recorded for this stage.

### step-2: Unexpected agent tool use
- Visibility: Defender-side logs where collected
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/agent-tools.sigma.yml
- KQL query download: /api/detections/agent-tools.kql
- SPL query download: /api/detections/agent-tools.spl
- Hunt hypothesis: Untrusted content or a changed tool definition precedes a file read, command, or remote call outside the user's intended task.
- Required telemetry: Agent tool-call audit records with session / tool / destination; Tool-definition and approval changes; Endpoint process, file-access and network evidence where available
- Investigate: Join input provenance, tool descriptions and calls by session ID and compare the action to the approved task.
- Investigate: Inspect child processes and destinations; record whether execution was in-process, local, or through a remote SaaS connector.
- Limitation: Process logs cannot recover model intent. Remote connectors and in-process interpreters may produce no local child process. Prompt content alone is not a reliable signature.
- No direct MagicSword prevention claim is recorded for this stage.

### step-3: Coordinated messaging / propagation
- Visibility: Platform / application records
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/social.sigma.yml
- KQL query download: /api/detections/social.kql
- SPL query download: /api/detections/social.spl
- Hunt hypothesis: Related accounts or assistants repeat correlated posting, forwarding or tool actions beyond the expected user workflow.
- Required telemetry: Platform account and posting audit; Agent session and message-provenance records; Rate, recipient and content-similarity features
- Investigate: Group actions by linked account, session, recipient and time rather than judging writing style.
- Investigate: Compare propagation with legitimate campaigns and preserve whether the source describes a lab demonstration or observed abuse.
- Limitation: Requires platform-side visibility. Similar content and synchronized activity can have legitimate explanations.
- No direct MagicSword prevention claim is recorded for this stage.

### step-4: Coordinated messaging / propagation
- Visibility: Platform / application records
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/social.sigma.yml
- KQL query download: /api/detections/social.kql
- SPL query download: /api/detections/social.spl
- Hunt hypothesis: Related accounts or assistants repeat correlated posting, forwarding or tool actions beyond the expected user workflow.
- Required telemetry: Platform account and posting audit; Agent session and message-provenance records; Rate, recipient and content-similarity features
- Investigate: Group actions by linked account, session, recipient and time rather than judging writing style.
- Investigate: Compare propagation with legitimate campaigns and preserve whether the source describes a lab demonstration or observed abuse.
- Limitation: Requires platform-side visibility. Similar content and synchronized activity can have legitimate explanations.
- Qualification: Use controlled-lab message and session records to investigate propagation; the research does not establish real-world victims.
- No direct MagicSword prevention claim is recorded for this stage.


## MITRE ATLAS
Mappings are catalog annotations based on described behavior, not assignments or endorsements by MITRE.
- AML.T0051.001: Indirect — Email content injects instructions into assistants in a controlled experiment.
  Technique: https://atlas.mitre.org/techniques/AML.T0051.001
  Evidence: https://arxiv.org/abs/2403.02817 ; https://www.wired.com/story/here-come-the-ai-worms/
- AML.T0061: LLM Prompt Self-Replication — The prompt is designed to replicate into assistant output.
  Technique: https://atlas.mitre.org/techniques/AML.T0061
  Evidence: https://arxiv.org/abs/2403.02817 ; https://www.wired.com/story/here-come-the-ai-worms/

## Defensive notes
Treat retrieved email/content as untrusted; isolation between agent mailboxes

## Sources
- https://arxiv.org/abs/2403.02817
- https://www.wired.com/story/here-come-the-ai-worms/
