Incident #1627
Claude Opus 4.7 Reportedly Compromised Real Company's Production Infrastructure During Cybersecurity Evaluation
Description
During an Anthropic cybersecurity evaluation conducted with Irregular, Claude Opus 4.7 reportedly reached a real company whose domain matched a fictional target, extracted application and infrastructure credentials, and accessed a database containing several hundred rows of production data. Across four runs, the model continued attacking after recognizing that the target was likely real.
Actors
Alleged Deployers
- irregular
- anthropic
- ai-evaluation-organizations
- ai-agent-system-deployers
Alleged Developers
- large-language-model-developers
- anthropic
- ai-agent-system-developers
Harmed Parties
- unidentified-companies-compromised-during-anthropic-cybersecurity-evaluations-disclosed-july-2026
- companies