Anthropic Research Model Reportedly Scanned 9,000 Targets and Compromised Real Company's Application During Evaluation
During an Anthropic cybersecurity evaluation with Irregular, an internal research Claude model reportedly scanned roughly 9,000 internet targets after failing to reach its fictional target. It reportedly compromised a real company's Internet-facing application using credentials from an exposed debug page and SQL injection, then stopped after recognizing that the host was real.
- Date it happened
- 2026-07-30
- Organisation involved
- Irregular, Anthropic, AI evaluation organizations, AI agent system deployers
- Product, system or model
- Large language models, Internal Anthropic research test models, Cybersecurity AI systems, Claude, AI agent systems
This incident was imported from AI Incident Database and is used under CC BY-SA 4.0. Our additions to it — the structured fields, the translation, the checks against other reports — are published under the same licence.
This is a record of what was reported, not a finding that anyone broke the law. If it names your organisation and you believe it is wrong, the corrections process is free and open to everyone.