AI-Powered Agents Steal 600,000 Credit Cards in Massive E-Commerce Attack Campaign
Security researchers at cybersecurity startup Gambit report that a financially motivated threat actor is using open-source AI agent frameworks to attack online retailers at scale, stealing more than 600,000 credit card records. The campaign has been active since at least July and continues as of September 22. In just five days, the attacker compromises at least 27 companies and launches more than 100 attacks, with the bulk of stolen card data coming from two victim companies.
The attack chain relies on three AI tools: the Strix penetration testing framework for scanning and vulnerability discovery, the Cairn autonomous exploitation engine for tasks like obtaining shell or admin access, and Hermes for campaign orchestration and post-exploitation decisions using claude-opus-4.6. Strix runs 146 times against 138 hosts between August 23 and 31, accumulating 633 scanning hours. Hermes contains a persona called "SOUL - Red Team Operator" with 121 skills, 78 of which relate to attacks. The human operator, believed to be Chinese, provides only brief instructions and lets the AI agents execute the rest autonomously.
The attackers inject card skimmers into victim websites using methods tailored to their level of access and each site's architecture. Observed techniques include appending malicious code to legitimate JavaScript files, adding script tags to checkout pages, poisoning S3/CDN content and server-side caches, modifying database fields, altering Kubernetes deployments, and using cron jobs to restore skimmers after removal. Gambit researchers gain direct evidence of the campaign after accessing an attacker-operated staging server.