# APT42 Gemini phishing + Data Processing Agent attempt

- ID: apt42-gemini-phishing-data-agent-2025
- Reported: 2025-11-05
- Researcher: Google Threat Intelligence Group
- Organization: Google GTIG
- AI role: attacker_uses_ai_as_operator (AI as operator)
- Confidence in AI involvement: not assessed
- Research / borderline: false
- Last reviewed: 2026-10-20
- Entry page: https://openattacks.ai/attacks/apt42-gemini-phishing-data-agent-2025/
- Entry JSON: https://openattacks.ai/api/attacks/apt42-gemini-phishing-data-agent-2025.json
- Browse title: APT42 uses Gemini for phishing and a 'Data Processing Agent'
- Editorial summary: Iranian APT42 used Gemini to draft phishing lures and attempted to build an agent that turns natural language into SQL queries over sensitive personal data.
- Evidence class (catalog annotation): Provider report
- Source-stated target environments: Provider-side
- Stage hunts and conditional defenses: https://openattacks.ai/api/defenses/apt42-gemini-phishing-data-agent-2025.json

## Technique
Iranian APT42 used Gemini for phishing lure drafting, translation, and geopolitical research. Also attempted to build a 'Data Processing Agent' that turns natural language into SQL over sensitive personal schemas (phone→owner, travel patterns).

## Stack relevance (editorial)
Assessment: attacker\_tool\_only. Editorial applicability reviewed against the catalog source account; not a scan or independent incident verification.
The named AI product is used by the attacker. No reviewed mapping from owning that product to the reported victim conditions is available.
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
- [Gemini](https://gemini.google.com/)
- planned NL-to-SQL data agent

## Other tooling
- unknown

## Victims and sectors
Think-tank and geopolitics-related phishing targets; Israeli defense research noted

## Target geography
- unknown

## Attribution
APT42; Iranian government-backed

## Scale and metrics
unknown

## Attack flow
Catalog reconstruction of the supplied source account. Unknowns and research caveats are preserved.
### step-1: Actor requests lure and research help [access]
APT42 uses geopolitical research and translated phishing material.
Evidence: https://cloud.google.com/blog/topics/threat-intelligence/threat-actor-usage-of-ai-tools/

### step-2: Gemini supports content generation [ai]
The model drafts lures and assists a proposed natural-language data-processing agent.
Evidence: https://cloud.google.com/blog/topics/threat-intelligence/threat-actor-usage-of-ai-tools/

### step-3: Phishing and agent development [execution]
The reported activity includes phishing preparation and attempted SQL-over-sensitive-schema tooling.
Evidence: https://cloud.google.com/blog/topics/threat-intelligence/threat-actor-usage-of-ai-tools/

### step-4: Agent deployment is unconfirmed [unknown]
The data-processing agent is described as an attempt, not a confirmed deployed capability.
Evidence: https://cloud.google.com/blog/topics/threat-intelligence/threat-actor-usage-of-ai-tools/

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: Provider-side abuse investigation
- Visibility: Provider / operator records
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/provider.sigma.yml
- KQL query download: /api/detections/provider.kql
- SPL query download: /api/detections/provider.spl
- Hunt hypothesis: A model-provider investigation correlates related accounts, repeated offensive requests and shared infrastructure or exposed operator sessions.
- Required telemetry: Provider-owned account / request audit; Abuse-review findings and linked-account context; Lawfully available exposed operator-session evidence
- Investigate: Correlate accounts, request rates, infrastructure and source-described behavior in provider-owned records.
- Investigate: For victim-side defense, pivot to the reported execution or access stage rather than trying to detect attacker-side prompts.
- Limitation: 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.
- Qualification: Research and translated lure requests are provider-side evidence, not a victim-side AI detector.
- No direct MagicSword prevention claim is recorded for this stage.

### step-2: Provider-side abuse investigation
- Visibility: Provider / operator records
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/provider.sigma.yml
- KQL query download: /api/detections/provider.kql
- SPL query download: /api/detections/provider.spl
- Hunt hypothesis: A model-provider investigation correlates related accounts, repeated offensive requests and shared infrastructure or exposed operator sessions.
- Required telemetry: Provider-owned account / request audit; Abuse-review findings and linked-account context; Lawfully available exposed operator-session evidence
- Investigate: Correlate accounts, request rates, infrastructure and source-described behavior in provider-owned records.
- Investigate: For victim-side defense, pivot to the reported execution or access stage rather than trying to detect attacker-side prompts.
- Limitation: 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.
- No direct MagicSword prevention claim is recorded for this stage.

### step-3: Lure → user action / delivery
- Visibility: Defender-side logs where collected
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/phishing.sigma.yml
- KQL query download: /api/detections/phishing.kql
- SPL query download: /api/detections/phishing.spl
- Hunt hypothesis: An impersonating message, ad or website leads to a suspicious download, consent request, pasted command or payment instruction.
- Required telemetry: Email / secure-web-gateway records; Browser redirects, downloads and URL reputation; User reports and downstream execution / identity events
- Investigate: Reconstruct redirect and delivery provenance using original report indicators, without visiting payload URLs.
- Investigate: Correlate the click with the actual download, consent or execution; verify the sender through an independent channel.
- Limitation: Polished text, AI branding and a novel domain do not prove maliciousness or AI generation. Follow-on evidence matters.
- Qualification: The data-processing agent's deployment is unconfirmed; the hunt concerns delivery of phishing messages only.
- No direct MagicSword prevention claim is recorded for this stage.

### step-4: No source-backed runtime hunt yet
- Visibility: Not established
- Query origin: catalog_authored; status: not_applicable; log scope: gap
- Hunt hypothesis: The supplied account does not establish a deployed victim-side behavior for this stage.
- Required telemetry: not assessed
- Investigate: Obtain a source-backed procedure and identify which party could observe it before drafting a detection.
- Limitation: Marketing claims, unknown steps and unconfirmed deployments are not detection coverage. No rule is generated for this stage.
- Qualification: The supplied account leaves this stage unestablished. Obtain a source-backed procedure before proposing a runtime query.
- 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.T0016.002: Generative AI — The supplied source explicitly describes generative-model tooling assisting the reported activity; this mapping does not establish additional autonomy or victim impact.
  Technique: https://atlas.mitre.org/techniques/AML.T0016.002
  Evidence: https://cloud.google.com/blog/topics/threat-intelligence/threat-actor-usage-of-ai-tools/

## Defensive notes
Phishing awareness for AI-polished lures; monitor for novel NL-SQL agents on sensitive DBs

## Sources
- https://cloud.google.com/blog/topics/threat-intelligence/threat-actor-usage-of-ai-tools/
