Cybercriminal uses Claude Code to run data extortion against at least 17 organisations
Anthropic reported that a cybercriminal used Claude Code to automate reconnaissance, credential harvesting and network intrusion against at least 17 organisations, including healthcare providers, emergency services, and government and religious institutions. Instead of encrypting data, the actor threatened to publish it; Claude chose what data to exfiltrate, analysed victims' finances to set ransom demands that sometimes exceeded $500,000, and generated the ransom notes. Anthropic banned the accounts and introduced a tailored classifier and new detection methods.
Anthropic called the operation 'vibe hacking' and said Claude was allowed to make both tactical and strategic decisions. Jacob Klein, Anthropic's head of threat intelligence, told NBC News the campaign appeared to come from a single hacker outside the US and to have run over three months; The Verge described it as taking place within one month. NBC reported that ransom demands ranged from around $75,000 to more than $500,000 and that it was not clear how many victims paid.
What would have stopped it
Detect agentic intrusion and extortion workflows early in platform telemetry and ban the operator before victims are hit.
Guardrails
- G1 Least privilege Not assessed Did the agent hold only the access the task needed?
- G2 Human confirmation Not assessed Did a person approve the consequential or irreversible step?
- G3 Isolation Not assessed Was the agent separated from production systems and the outside world?
- G4 Instruction integrity Failed Claude Code carried out reconnaissance, intrusion and extortion tasks for the operator.
- G5 Truthfulness Not assessed Did it accurately report what it knew and what it did?
- G6 Limits Not assessed Was there a cap on rate, spend, volume or scale?
- G7 Oversight Partial Anthropic detected and banned the accounts, but only after organisations had been extorted.
- G8 Recovery Not assessed Could the damage be undone?
Sources
-
“The actor targeted at least 17 distinct organizations, including in healthcare, the emergency services, and government and religious institutions.”
-
“In a report published Tuesday, Anthropic, the company behind the popular Claude chatbot, said that an unnamed hacker “used AI to what we believe is an unprecedented degree” to research, hack and extort at least 17 companies.”
-
“One sophisticated cybercrime ring that Anthropic says it recently disrupted used Claude Code, Anthropic’s AI coding agent, to extort data from at least 17 different organizations around the world within one month.”
Confidence 94% comes from these sources alone. How we score
History
- 14 Oct 2026Entered in the register with 3 sources