AI evaluation organizations
Incidents involved as Deployer
インシデント 162716 Report
Claude Opus 4.7 Reportedly Compromised Real Company's Production Infrastructure During Cybersecurity Evaluation
2026-07-30
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.
もっとインシデント 162816 Report
Claude Mythos 5 Reportedly Published Malicious PyPI Package That Compromised Real Security Company During Evaluation
2026-07-30
During an Anthropic cybersecurity evaluation with Irregular, Claude Mythos 5 reportedly created and published a malicious Python package to PyPI while pursuing a fictional target. The package was reportedly available for about an hour and ran on 15 real systems. On a security company's scanner, it reportedly exfiltrated credentials that Claude then used to access additional company infrastructure.
もっとインシデント 162916 Report
Anthropic Research Model Reportedly Scanned 9,000 Targets and Compromised Real Company's Application During Evaluation
2026-07-30
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.
もっとインシデント 17515 Report
Anthropic AI Agent Reportedly Submitted a Fabricated Homicide Tip to Police in Philadelphia
2026-07-18
During an evaluation by AI developer Anthropic, a Claude Haiku 4.5 AI agent reportedly submitted fabricated eyewitness information about an unsolved homicide through a police tip form in Philadelphia. The submission entered the website's tip records, creating a risk of misleading investigators, but police said its email was flagged as spam and never forwarded for investigative review.
もっと関連団体
同じインシデントに関連するその他のエンティティ。たとえば、インシデントの開発者がこのエンティティで、デプロイヤーが別のエンティテ ィである場合、それらは関連エンティティとしてマークされます。
関連団体
Anthropic
開発者と提供者の両方の立場で関わったインシデント
- インシデント 162716 レポート
Claude Opus 4.7 Reportedly Compromised Real Company's Production Infrastructure During Cybersecurity Evaluation
- インシデント 162816 レポート
Claude Mythos 5 Reportedly Published Malicious PyPI Package That Compromised Real Security Company During Evaluation