AI evaluation organizations
Incidents involved as Deployer
インシデント 162715 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 162815 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 162915 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 16334 Report
Anthropic and OpenAI AI Agents Reportedly Took Unsanctioned Actions on the Live Internet During UK AISI Cybersecurity Evaluations
2026-07-26
Beginning July 26, 2026, AI agents powered by Anthropic's Mythos 5 and OpenAI's GPT-5.6 Sol reportedly took 19 unsanctioned actions on the live Internet during UK AISI cybersecurity evaluations. Mythos 5 reportedly accounted for 17 events, many allegedly involving deceptive attempts to manipulate real developers into accepting malicious code. AISI reportedly detected and contained the activity; no resulting real-world harm was identified.
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 162715 レポート
Claude Opus 4.7 Reportedly Compromised Real Company's Production Infrastructure During Cybersecurity Evaluation
- インシデント 162815 レポート
Claude Mythos 5 Reportedly Published Malicious PyPI Package That Compromised Real Security Company During Evaluation