Case · DiggingBeagle record
Anthropic reports that a single French-speaking actor used Claude and sub-agent workflows against European political, media, think-tank and SaaS targets, gaining internal access to at least 14 of 42 tracked entities.
Anthropic's GTG-50029 case study covering spring and early-summer 2026 activity. Victim identities are largely withheld in the public report.
GTG-50029 compresses several capabilities that usually belong to a larger team. Anthropic reports that one actor built a Rust scanner for exposed API keys, rotated stolen keys through a proxy layer, and used an agentic framework whose sub-agents handled reconnaissance, code review and validation of findings from multiple models.
The campaign combined familiar web compromise with custom exploit development. Anthropic says the actor used Claude to develop and debug a previously undocumented WordPress re-installation race condition that created rogue administrator accounts, succeeding against at least four victim sites. In another target, agents iterated over an exposed search endpoint and exfiltrated about 140,000 records containing political opinions.
Across 42 tracked targets, Anthropic says the actor obtained internal access to at least 14. The report also describes webshells, credential-harvesting plugins, poisoned backups and a doxxing platform built by the same operator. The important shift is operational scale, not that every underlying technique was new.
A custom Rust scanner identifies and validates keys in public containers and other exposed material.
Boundary: public exposure / stolen credentials
The actor blends model traffic with legitimate owners' usage.
Boundary: stolen credential / AI provider
Agent workflows perform pre-auth and post-auth recon, code review and finding validation.
Boundary: operator / multi-agent harness
Claude-assisted sessions produce and debug exploits such as the WordPress re-installation race condition.
Boundary: agent workflow / target application
Webshells, credential-harvesting plugins, poisoned backups and data-processing tooling support continued access and theft.
Boundary: victim environment / actor infrastructure
Anthropic's GTG-50029 indicator table begins on February 6.
Anthropic lists a set of VPN and datacenter exits beginning March 25.
Anthropic lists the campaign's browser-C2 hostname from May 13.
The report summarizes the campaign, target counts and data theft.
Locator: GTG-50029, political campaign platform
Anthropic reports approximately 140,000 exfiltrated records from one target.
Scope: Anthropic's aggregate estimate across tracked target activity.
Locator: GTG-50029, campaign scope
The report gives an estimated 12 to 26 GB of database dumps and a 15,000-message mailbox.
Locator: GTG-50029, campaign scope
Anthropic reports 42 tracked targets and internal access to at least 14.
Locator: GTG-50029, overview
Anthropic describes one French-speaking actor using an agentic framework to manage multiple offensive sub-agents.
Locator: GTG-50029, novel exploitation
The report attributes development and debugging of the race-condition exploit to the actor's Claude-assisted workflow.
chart
Anthropic GTG-50029 threat-intelligence investigation.
| Measure | target entities |
|---|---|
| Tracked targets | 42 |
| Internal access | 14 |
diagram
Scanner finds and validates public keys
Rotates stolen key usage
Recon, code review and finding validation
Includes WordPress race-condition development
Webshells, credential plugins and poisoned backups
Staging, search and exfiltration
Agentic tooling can give a single operator enough throughput to manage discovery, exploit development, persistence and stolen-data processing across many targets. Defenders should watch for the orchestration layer, repeated key-validation infrastructure and machine-paced adaptation across otherwise unrelated victims.
DiggingBeagle. “GTG-50029 used agentic workflows across a European hacktivist campaign.” First seen Feb 6, 2026. https://diggingbeagle.com/cases/gtg-50029-used-agentic-workflows-across-a-european-hacktivist-campaign/
Citation guidanceWhy this archive exists
DiggingBeagle is a non profit research project documenting AI security incidents, agent failures, vulnerabilities and AI-assisted operations. A case keeps its claims beside the sources that support, contest or limit them. Later updates stay visible, so a reader can see when the account changed.
We publish case reconstructions, dated reporting and analysis across records. Each has a different evidentiary role. About the project and our methodology explain how the work is reviewed.