AIA-018 Claude Code used in a data-extortion operation against at least 17 organizations, per Anthropic

ID: AIA-018
Category: AI AI agent incident
Disclosed: 2025-08
Systems: Claude Code
Harm type: Misuse
Status: confirmed by vendor
Anthropic published the report.

Summary

Anthropic reported disrupting an actor that "used Claude Code to commit large-scale theft and extortion of personal data." The actor targeted "at least 17 distinct organizations" and threatened to publish the data, with ransom demands that "sometimes exceeded $500,000."

Controls

Controls that could prevent, detect, or support recovery from this kind of failure. Mappings are editorial judgments made by the method, not findings about what any party should have done.

NIST AI RMF

MANAGE 4.1 Post-deployment monitoring is in place
MEASURE 2.7 Security and resilience are evaluated and documented

NIST SP 800-53

SI-4 System Monitoring
AC-2 Account Management

Human-approval (JCR) checkpoint

not applicable

Sources

anthropic.com primary link checked 2026-10-31, HTTP 200
Published Aug 27, 2025
https://www.anthropic.com/news/detecting-countering-misuse-aug-2025

Corrections

No corrections recorded.

To report an error in this entry, see corrections.