Detection queries Provider reportProvider-side

TEMP.Zagros / MuddyWater use Gemini for custom malware

Iranian MuddyWater used 'student project' pretexts to get Gemini's help with web shells and C2. Pasting in a C2 domain and key exposed their infrastructure and aided disruption.

What happened

Iranian TEMP.Zagros (MuddyWater) used Gemini with 'student project' pretexts to develop custom malware (web shells, Python C2). OPSEC failure: pasted script with hard-coded C2 domain and encryption key into Gemini, aiding disruption.

Read the original source

How it happened

Select a stage to explore its defenses
Detect this stage
Detect this stage
Detect this stage
Detect this stage
Select a stage · Drag to explore · + / − to zoom · Dashed edges are loopsSelect a stage · Arrows show reported connectionsReported sequence
Read the flow as text & sources

A catalog reconstruction of the supplied source account. Unknown steps remain explicit; an edge describes the reported relationship between steps.

  1. 01 · Actor seeks custom malware assistance

    Requests use student-project pretexts.

    Hunt: A model-provider investigation correlates related accounts, repeated offensive requests and shared infrastructure or exposed operator sessions.

    Attacker-side planning is generally absent from victim SIEM logs. These templates require provider-owned audit data and do not identify AI use from a victim process alone.

    Source for step 1
  2. 02 · Gemini helps develop code

    Reported tasks include web shells and a Python C2.

    Hunt: A model-provider investigation correlates related accounts, repeated offensive requests and shared infrastructure or exposed operator sessions.

    Attacker-side planning is generally absent from victim SIEM logs. These templates require provider-owned audit data and do not identify AI use from a victim process alone.

    Source for step 2
  3. 03 · Actor pastes operational details

    Submitted code contains a hard-coded C2 domain and encryption key.

    Hunt: A model-provider investigation correlates related accounts, repeated offensive requests and shared infrastructure or exposed operator sessions.

    Attacker-side planning is generally absent from victim SIEM logs. These templates require provider-owned audit data and do not identify AI use from a victim process alone.

    Source for step 3
  4. 04 · Operational exposure aids disruption

    The research describes an OPSEC failure, rather than disclosing a complete downstream victim chain.

    Hunt: A model-provider investigation correlates related accounts, repeated offensive requests and shared infrastructure or exposed operator sessions.

    Attacker-side planning is generally absent from victim SIEM logs. These templates require provider-owned audit data and do not identify AI use from a victim process alone.

    Source for step 4

Why it matters

Reported entry point: Phishing from compromised corporate mailboxes (group TTP). Reported impact: The research describes an OPSEC failure, rather than disclosing a complete downstream victim chain; using the named AI products does not by itself establish exposure.

Read the original report

What you can do

Protection & prevention

Phishing-resistant controls; detect new custom C2; model providers can disrupt via leaked infra

Catalog defensive guidance based on the reported behavior. Confirm scope and current mitigations in the original source.

Review the original guidance
Investigate each phase

Detection queries

Draft query starters grouped by the attack stages where they apply.

Download stage pack

Start with the logs you collect. Each hunt identifies its required visibility, field mapping and limits. Queries are catalog-authored drafts using reusable behavior profiles; test with known activity and your normal baseline before alerting.

01Actor seeks custom malware assistanceProvider-side abuse investigationCustom schema · Draft

Requests use student-project pretexts.

What to look for

A model-provider investigation correlates related accounts, repeated offensive requests and shared infrastructure or exposed operator sessions.

The described development requests require provider-side records; a student-project pretext is not a reliable standalone signature.

Visibility: Provider / operator records

Required logs

  • Provider-owned account / request audit
  • Abuse-review findings and linked-account context
  • Lawfully available exposed operator-session evidence

Coverage limit. Attacker-side planning is generally absent from victim SIEM logs. These templates require provider-owned audit data and do not identify AI use from a victim process alone.

Custom-schema candidates, not out-of-box detectors. Map your application / cloud / platform logs to EventType, Actor, Asset, Action, Target and CorrelationId. KQL uses a custom OpenAttacksAudit_CL table; SPL uses openattacks:audit. EventType values are proposed normalization names, not native vendor event names. Correlation and environment-specific alert logic remain to be built.

Sigma
Draft SigmaDownload Sigma
title: Hunt - Provider-side abuse investigation
id: c8c1edc0-c79a-4644-a876-2c1a6cb9a438
status: experimental
description: A model-provider investigation correlates related accounts,
  repeated offensive requests and shared infrastructure or exposed operator
  sessions.
author: MagicSword OpenAttacks catalog
date: 2026-10-23
falsepositives:
  - Authorized activity matching this broad hunt; baseline and investigate
    before alerting.
level: low
logsource:
  category: application
  product: openattacks_audit
  definition: Custom normalized audit schema; map EventType, Actor, Asset, Action,
    Target and CorrelationId from the required source logs first.
detection:
  selection:
    EventType:
      - model.request
  condition: selection
KQL
Draft KQLDownload KQL
// SCHEMA TEMPLATE: create/map this custom table before use; not a built-in Sentinel table.
// OpenAttacksAudit_CL: TimeGenerated(datetime), EventType/Actor/Asset/Action/Target/CorrelationId(string).
// Selects candidates only. Apply the stage hypothesis and correlation steps before alerting.
OpenAttacksAudit_CL
| where TimeGenerated > ago(7d)
| where EventType in ("model.request")
| project TimeGenerated, EventType, Actor, Asset, Action, Target, CorrelationId
| order by TimeGenerated desc
SPL
Draft SPLDownload SPL
sourcetype="openattacks:audit"
EventType IN ("model.request")
| table _time EventType Actor Asset Action Target CorrelationId
| sort - _time
Investigation steps
  1. Correlate accounts, request rates, infrastructure and source-described behavior in provider-owned records.
  2. For victim-side defense, pivot to the reported execution or access stage rather than trying to detect attacker-side prompts.
02Gemini helps develop codeProvider-side abuse investigationCustom schema · Draft

Reported tasks include web shells and a Python C2.

What to look for

A model-provider investigation correlates related accounts, repeated offensive requests and shared infrastructure or exposed operator sessions.

Visibility: Provider / operator records

Required logs

  • Provider-owned account / request audit
  • Abuse-review findings and linked-account context
  • Lawfully available exposed operator-session evidence

Coverage limit. Attacker-side planning is generally absent from victim SIEM logs. These templates require provider-owned audit data and do not identify AI use from a victim process alone.

Custom-schema candidates, not out-of-box detectors. Map your application / cloud / platform logs to EventType, Actor, Asset, Action, Target and CorrelationId. KQL uses a custom OpenAttacksAudit_CL table; SPL uses openattacks:audit. EventType values are proposed normalization names, not native vendor event names. Correlation and environment-specific alert logic remain to be built.

Sigma
Draft SigmaDownload Sigma
title: Hunt - Provider-side abuse investigation
id: c8c1edc0-c79a-4644-a876-2c1a6cb9a438
status: experimental
description: A model-provider investigation correlates related accounts,
  repeated offensive requests and shared infrastructure or exposed operator
  sessions.
author: MagicSword OpenAttacks catalog
date: 2026-10-23
falsepositives:
  - Authorized activity matching this broad hunt; baseline and investigate
    before alerting.
level: low
logsource:
  category: application
  product: openattacks_audit
  definition: Custom normalized audit schema; map EventType, Actor, Asset, Action,
    Target and CorrelationId from the required source logs first.
detection:
  selection:
    EventType:
      - model.request
  condition: selection
KQL
Draft KQLDownload KQL
// SCHEMA TEMPLATE: create/map this custom table before use; not a built-in Sentinel table.
// OpenAttacksAudit_CL: TimeGenerated(datetime), EventType/Actor/Asset/Action/Target/CorrelationId(string).
// Selects candidates only. Apply the stage hypothesis and correlation steps before alerting.
OpenAttacksAudit_CL
| where TimeGenerated > ago(7d)
| where EventType in ("model.request")
| project TimeGenerated, EventType, Actor, Asset, Action, Target, CorrelationId
| order by TimeGenerated desc
SPL
Draft SPLDownload SPL
sourcetype="openattacks:audit"
EventType IN ("model.request")
| table _time EventType Actor Asset Action Target CorrelationId
| sort - _time
Investigation steps
  1. Correlate accounts, request rates, infrastructure and source-described behavior in provider-owned records.
  2. For victim-side defense, pivot to the reported execution or access stage rather than trying to detect attacker-side prompts.
03Actor pastes operational detailsProvider-side abuse investigationCustom schema · Draft

Submitted code contains a hard-coded C2 domain and encryption key.

What to look for

A model-provider investigation correlates related accounts, repeated offensive requests and shared infrastructure or exposed operator sessions.

Visibility: Provider / operator records

Required logs

  • Provider-owned account / request audit
  • Abuse-review findings and linked-account context
  • Lawfully available exposed operator-session evidence

Coverage limit. Attacker-side planning is generally absent from victim SIEM logs. These templates require provider-owned audit data and do not identify AI use from a victim process alone.

Custom-schema candidates, not out-of-box detectors. Map your application / cloud / platform logs to EventType, Actor, Asset, Action, Target and CorrelationId. KQL uses a custom OpenAttacksAudit_CL table; SPL uses openattacks:audit. EventType values are proposed normalization names, not native vendor event names. Correlation and environment-specific alert logic remain to be built.

Sigma
Draft SigmaDownload Sigma
title: Hunt - Provider-side abuse investigation
id: c8c1edc0-c79a-4644-a876-2c1a6cb9a438
status: experimental
description: A model-provider investigation correlates related accounts,
  repeated offensive requests and shared infrastructure or exposed operator
  sessions.
author: MagicSword OpenAttacks catalog
date: 2026-10-23
falsepositives:
  - Authorized activity matching this broad hunt; baseline and investigate
    before alerting.
level: low
logsource:
  category: application
  product: openattacks_audit
  definition: Custom normalized audit schema; map EventType, Actor, Asset, Action,
    Target and CorrelationId from the required source logs first.
detection:
  selection:
    EventType:
      - model.request
  condition: selection
KQL
Draft KQLDownload KQL
// SCHEMA TEMPLATE: create/map this custom table before use; not a built-in Sentinel table.
// OpenAttacksAudit_CL: TimeGenerated(datetime), EventType/Actor/Asset/Action/Target/CorrelationId(string).
// Selects candidates only. Apply the stage hypothesis and correlation steps before alerting.
OpenAttacksAudit_CL
| where TimeGenerated > ago(7d)
| where EventType in ("model.request")
| project TimeGenerated, EventType, Actor, Asset, Action, Target, CorrelationId
| order by TimeGenerated desc
SPL
Draft SPLDownload SPL
sourcetype="openattacks:audit"
EventType IN ("model.request")
| table _time EventType Actor Asset Action Target CorrelationId
| sort - _time
Investigation steps
  1. Correlate accounts, request rates, infrastructure and source-described behavior in provider-owned records.
  2. For victim-side defense, pivot to the reported execution or access stage rather than trying to detect attacker-side prompts.
04Operational exposure aids disruptionProvider-side abuse investigationCustom schema · Draft

The research describes an OPSEC failure, rather than disclosing a complete downstream victim chain.

What to look for

A model-provider investigation correlates related accounts, repeated offensive requests and shared infrastructure or exposed operator sessions.

Visibility: Provider / operator records

Required logs

  • Provider-owned account / request audit
  • Abuse-review findings and linked-account context
  • Lawfully available exposed operator-session evidence

Coverage limit. Attacker-side planning is generally absent from victim SIEM logs. These templates require provider-owned audit data and do not identify AI use from a victim process alone.

Custom-schema candidates, not out-of-box detectors. Map your application / cloud / platform logs to EventType, Actor, Asset, Action, Target and CorrelationId. KQL uses a custom OpenAttacksAudit_CL table; SPL uses openattacks:audit. EventType values are proposed normalization names, not native vendor event names. Correlation and environment-specific alert logic remain to be built.

Sigma
Draft SigmaDownload Sigma
title: Hunt - Provider-side abuse investigation
id: c8c1edc0-c79a-4644-a876-2c1a6cb9a438
status: experimental
description: A model-provider investigation correlates related accounts,
  repeated offensive requests and shared infrastructure or exposed operator
  sessions.
author: MagicSword OpenAttacks catalog
date: 2026-10-23
falsepositives:
  - Authorized activity matching this broad hunt; baseline and investigate
    before alerting.
level: low
logsource:
  category: application
  product: openattacks_audit
  definition: Custom normalized audit schema; map EventType, Actor, Asset, Action,
    Target and CorrelationId from the required source logs first.
detection:
  selection:
    EventType:
      - model.request
  condition: selection
KQL
Draft KQLDownload KQL
// SCHEMA TEMPLATE: create/map this custom table before use; not a built-in Sentinel table.
// OpenAttacksAudit_CL: TimeGenerated(datetime), EventType/Actor/Asset/Action/Target/CorrelationId(string).
// Selects candidates only. Apply the stage hypothesis and correlation steps before alerting.
OpenAttacksAudit_CL
| where TimeGenerated > ago(7d)
| where EventType in ("model.request")
| project TimeGenerated, EventType, Actor, Asset, Action, Target, CorrelationId
| order by TimeGenerated desc
SPL
Draft SPLDownload SPL
sourcetype="openattacks:audit"
EventType IN ("model.request")
| table _time EventType Actor Asset Action Target CorrelationId
| sort - _time
Investigation steps
  1. Correlate accounts, request rates, infrastructure and source-described behavior in provider-owned records.
  2. For victim-side defense, pivot to the reported execution or access stage rather than trying to detect attacker-side prompts.
Technical detailsTooling, impact & MITRE ATLAS

Attack context

AI's role
AI as operator
Initial access
Phishing from compromised corporate mailboxes (group TTP)

Tooling as reported

AI products, models and artifacts

Other tooling

Reported attribution

TEMP.Zagros / MUDDYCOAST / MuddyWater; Iranian state-sponsored

Structured attribution

Actor
TEMP.Zagros
Country
Iran
Motivation
nation-state

Detection rules

  • Review attack-specific indicatorsGUIDANCE

    Monitor for the techniques described in TEMP.Zagros / MuddyWater Gemini-assisted custom malware. Refer to sources for specific IOCs and TTPs.

Linked threat actors

Source defensive notes

Phishing-resistant controls; detect new custom C2; model providers can disrupt via leaked infra

MITRE ATLAS

AI-specific catalog annotations based on the reported behavior; these are not MITRE case-study assignments.

AML.T0016.002Generative AI

The supplied source explicitly describes generative-model tooling assisting the reported activity; this mapping does not establish additional autonomy or victim impact. Source

Sources & research credit

1 source

Research by Google Threat Intelligence Group · Google GTIG

  1. cloud.google.com
Record & downloads
Source record name
TEMP.Zagros / MuddyWater Gemini-assisted custom malware
Entry ID
temp-zagros-gemini-malware-dev-2025
Catalog review
October 20, 2026
Category
adversary-use-of-ai
AI involvement confidence
confirmed