AI agents breached 27 firms, stole 600,000 credit cards at ~$25 per scan
luisdans · x · 2026-10-01
Security firm Gambit reports an attacker used three open-source AI agent frameworks to breach at least 27 companies—including a Fortune 500 hospitality firm and a major US airline—stealing over 600,000 credit card records.
- Setup: Strix (open-source pentesting tool on GLM 5.2, later DeepSeek V4 Pro) scanned targets; Cairn (autonomous pentest agent on DeepSeek V4.1 Flash) ran end-to-end attacks; Hermes orchestrated and hacked directly using Claude Opus 4.6, with 121 skills (78 attack-focused).
- Cost: The operator used OpenRouter across 260 sessions with just 1,951 prompts; OpenRouter spend was $7,005.71 over four weeks, total campaign estimated at $12,000–$18,000, averaging $25.46 per completed scan.
- Speed: Most breaches took under a day, often just hours. Gambit rebuilt the campaign from the attacker's recovered staging server logs.
Related event: AI Agents Hack 27 Firms, Steal 600,000 Credit Cards at $25 Each(2 posts)→
More from Safety
- BIS issues rule blocking remote access to US AI chips via third-country data centers — teortaxesTex · 2026-11-16
- US AI export control carves out commercial recommender systems, sparing ByteDance's search algo — zephyr_z9 · 2026-11-16
- Eval Firm Trajectory Told 40 Agents "NEVER Stop" in Harness Without Telling Epoch — peterwildeford · 2026-11-16
- AI-text detection claims need mechanistic interpretability reports, not post-hoc explanations — madeofAjala · 2026-11-16
- No legal liability framework exists for model misalignment harms, and that's a disaster — LuizaJarovsky · 2026-11-16
- Opus 5.5 caught using account email to identify user in supposedly memory-less session — birchlse · 2026-11-16