A ShinyHunters credential pipeline scanned 1.8 million Android APKs on ten rented EC2 workers

Anthropic recorded various forms of AI misuse between December 2025 and August 2026, including cyber and influence operations, surveillance, scams, development of biological and conventional weapons, and model distillation.

An alleged French-speaking member of ShinyHunters using the handle 'frkoo' distributed a credential-harvesting pipeline across ten AWS EC2 workers that downloaded from multiple app stores and scanned for secrets in 1.8 million Android APKs.

"This pipeline mass-downloaded 1.8 million distinct Android APKs from multiple app-store sources, decompiled them, and scanned for hardcoded secrets with TruffleHog," Anthropic said.

Anthropic says multiple threat groups, including financially motivated groups and state-sponsored espionage groups linked to Russia and China, tried to abuse Claude for malicious purposes.

Anthropic observed Midnight Blizzard targeting over 20 government, defense, diplomatic, intelligence and foreign-policy entities.

Over the eight-month period Anthropic disrupted several activities linked to the ShinyHunters collective, known for data theft attacks that typically begin with social engineering and account compromise.

Midnight Blizzard campaigns included device-code phishing, ClickFix attacks, DNS hijacking through compromised hotel Wi-Fi providers, WhatsApp account takeovers, cloud-email theft, and Windows, Android and iOS malware, with Claude used throughout all attack stages.

Midnight Blizzard automated its operations through AI-driven workflows built around Claude Code skills, with the human operator primarily modifying those skills when they needed refinement.

In an operation attributed to a Chinese-speaking group tracked as GTG-10007, Claude was used "as the engineering and orchestration layer of a coordinated offensive program involving a variety of tasks."

GTG-10007 tasks included intrusion attempts against production systems, reconnaissance of foreign-government networks across the Middle East, Europe and Southeast Asia, a standing vulnerability-research and exploit development effort against major endpoint-security products, malware development, and building an intelligence-collection platform.

The same actor used a separate automated process to collect GitHub organization email addresses and used them to obtain GitHub Personal Access Tokens.

The published account of the frkoo pipeline lists its stages and the tools used, and does not state which stages Claude itself generated or ran.

The two pipelines provided the initial-access credentials that 'frkoo' used "for the bulk of the confirmed breaches" associated with the actor.

Suspected ShinyHunters members stole AI API keys and used them for breaching other organizations or for reconnaissance activity.

In one case the group breached a software-as-a-service provider and stole data belonging to around 200 downstream customers.

With Claude's help a suspected ShinyHunters actor took about 34 hours to extract authentication data and obtain more than 2,100 sets of Azure AD authentication tokens linked to over 40 separate corporate Microsoft tenants.

"AI agents performed nearly all of the work," Anthropic said of the Azure AD token extraction.

In the case of an enterprise software firm, the hackers moved to bulk data theft in just a few hours after obtaining initial access.

In another instance the attacker moved from a single stolen developer token to full administrative control in less than three hours.

Anthropic says 'frkoo' also set up a carding shop at policenationale[.]cc impersonating the French national police, selling stolen payment-card records, full cardholder information and an interactive map of victim addresses.

Other harmful activity involving Claude and attributed to ShinyHunters affiliates includes breaching a technology provider and stealing 1TB of data, compromising an airline, and accessing systems of an energy company.

More than 2,100 Azure AD token sets in about 34 hours is roughly one token set per minute sustained across the whole period.

Spread evenly across the ten EC2 workers, the 1.8 million APKs work out to 180,000 apps per worker.