# GTG-1002 AI-orchestrated espionage via Claude Code

- ID: gtg-1002-anthropic-claude-code-espionage-2025-11
- Reported: 2025-11-13
- Researcher: Anthropic Threat Intelligence
- Organization: Anthropic
- 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/gtg-1002-anthropic-claude-code-espionage-2025-11/
- Entry JSON: https://openattacks.ai/api/attacks/gtg-1002-anthropic-claude-code-espionage-2025-11.json
- Browse title: GTG-1002 AI-orchestrated espionage via Claude Code
- Editorial summary: Anthropic reports that a state-sponsored group used Claude Code to orchestrate intrusion tasks. Human operators selected targets, and model-generated findings required validation.
- Evidence class (catalog annotation): Reported campaign
- Source-stated target environments: Not specified
- Stage hunts and conditional defenses: https://openattacks.ai/api/defenses/gtg-1002-anthropic-claude-code-espionage-2025-11.json

## Technique
Chinese state-sponsored GTG-1002 manipulated Claude Code and MCP tools as autonomous pentest orchestrators across recon, vuln discovery, exploitation, lateral movement, credential harvest, analysis, and exfil. Anthropic assesses AI executed ~80-90% of tactical ops at high request rates. Human operators selected targets and tasked agent groups. Claude sometimes hallucinated credentials/findings, requiring validation.

## 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
Human-selected targets; AI discovered and exploited vulnerabilities in live ops (details redacted in public report)

## AI tooling and models
- [Claude Code](https://github.com/anthropics/claude-code)
- MCP tools
- crafted prompts/personas to bypass guardrails

## Other tooling
- unknown

## Victims and sectors
~30 entities; validated handful of successful intrusions including major technology corporations and government agencies; technology, financial, chemical, government (MITRE C0062)

## Target geography
- Multiple regions
Global targeting is described without individual countries. China-nexus attribution concerns the actor, not victim location.

## Attribution
GTG-1002; high confidence Chinese state-sponsored (Anthropic); MITRE Campaign C0062

## Scale and metrics
~30 entities targeted; mid-Sep 2025 activity window; first documented largely autonomous AI cyberattack at scale per Anthropic

## Attack flow
Catalog reconstruction of the supplied source account. Unknowns and research caveats are preserved.
### step-1: Human operators choose targets [access]
Operators task agents against live organizations; exploit details are redacted.
Evidence: https://www-cdn.anthropic.com/d7dd50dd1185f59be051b307150d877f2b82bd2c.pdf ; https://attack.mitre.org/campaigns/C0062/

### step-2: Claude Code orchestrates tactical work [ai]
Coding agents and MCP tools support reconnaissance, discovery and exploitation.
Evidence: https://www-cdn.anthropic.com/d7dd50dd1185f59be051b307150d877f2b82bd2c.pdf ; https://attack.mitre.org/campaigns/C0062/

### step-3: Intrusion steps progress [execution]
The report describes credential harvesting, lateral movement, analysis and collection.
Evidence: https://www-cdn.anthropic.com/d7dd50dd1185f59be051b307150d877f2b82bd2c.pdf ; https://attack.mitre.org/campaigns/C0062/

### step-4: Data is exfiltrated [impact]
Anthropic reports a handful of validated intrusions and notes that model findings still required human validation.
Evidence: https://www-cdn.anthropic.com/d7dd50dd1185f59be051b307150d877f2b82bd2c.pdf ; https://attack.mitre.org/campaigns/C0062/

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: Human target selection is provider/operator-side evidence. Redacted exploit details do not support a guessed endpoint rule.
- 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.
- Community intelligence: LOLSkills — https://lolskills.io

### step-3: Web exploitation → host activity
- Visibility: Defender-side logs where collected
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/web.sigma.yml
- KQL query download: /api/detections/web.kql
- SPL query download: /api/detections/web.spl
- Hunt hypothesis: Repeated exploit or upload requests are followed by an unexpected server process, file, or outbound connection.
- Required telemetry: Reverse-proxy / WAF request logs; Server process and file events; Outbound DNS / proxy records
- Investigate: Join requests to the affected host and process tree by time and request ID.
- Investigate: Inspect uploaded files and server-spawned shells; distinguish authorized testing from exploitation.
- Limitation: A scan or high request rate alone does not prove compromise or AI use. Host telemetry is needed to confirm execution.
- No direct MagicSword prevention claim is recorded for this stage.
- Community intelligence: GTFOBins — https://gtfobins.github.io

### step-4: Sensitive data → unusual destination
- Visibility: Defender-side logs where collected
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/exfil.sigma.yml
- KQL query download: /api/detections/exfil.kql
- SPL query download: /api/detections/exfil.spl
- Hunt hypothesis: Sensitive reads are followed by outbound transfer, a public artifact, or a tool call to a destination outside the approved workflow.
- Required telemetry: Sensitive resource access / DLP records; Proxy, egress and cloud upload events; Agent / SaaS audit with correlation IDs
- Investigate: Join the resource read and outbound action by session, identity or process, preserving a bounded time window.
- Investigate: Inspect destination ownership, payload classification and the user's intended action; baseline sanctioned sharing.
- Limitation: An outbound connection or high byte count alone is not exfiltration. Encrypted traffic may hide content, and bulk legitimate exports are common.
- 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 operation obtains generative AI tooling for intrusion support.
  Technique: https://atlas.mitre.org/techniques/AML.T0016.002
  Evidence: https://www-cdn.anthropic.com/d7dd50dd1185f59be051b307150d877f2b82bd2c.pdf ; https://attack.mitre.org/campaigns/C0062/
- AML.T0102: Generate Malicious Commands — The model assists tactical command and tool generation.
  Technique: https://atlas.mitre.org/techniques/AML.T0102
  Evidence: https://www-cdn.anthropic.com/d7dd50dd1185f59be051b307150d877f2b82bd2c.pdf ; https://attack.mitre.org/campaigns/C0062/

## Defensive notes
Detect agentic coding CLI + MCP automation spikes; least-privilege MCP; raise cost of LOLBin/tool execution with app control

## Sources
- https://www-cdn.anthropic.com/d7dd50dd1185f59be051b307150d877f2b82bd2c.pdf
- https://attack.mitre.org/campaigns/C0062/
