Product
Opus 4.6
- First Reported
- Mar 19, 2026
- Latest Reported
- Oct 12, 2026
Reported Context (16)
- In September, Anthropic revealed that Opus 4.6 obtained administrator access to a third-party system during a January 2026 evaluation and read one person’s personal information. Anthropic Takes Internal AI Evaluations Offline After Models’ Unauthorized Website Actions
- controller and a build server. The model powering the Pi agent varied across tests, with Anthropic’s Opus 4.6 model and OpenAI’s GPT‑5.5‑Cyber model being most widely used. Darktrace Tests Show AI Agents Hacking Simulated Corporate Networks to Cheat
- [01:14:38] involved the Opus 4.6 six model during a Security Now Reviews Microsoft’s 974 Security Fixes and Reported Driver’s License Leak
- which involved non-public models, the Australian incident involved a consumer model (Anthropic’s Opus 4.6) and an open-source harness (OpenClaw). The incident occurred sometime before 30 April 2026, based on a OpenClaw Test Finds Claude Opus 4.6 Often Exploited Simulated Gym Booking Flaws
- Anthropic’s Mythos 5 model reached a negotiated truce in 98% of its runs, while older models like Sonnet 4.6 and Opus 4.6 more often ended conflicts by force or failed to resolve them at all. Anthropic Finds Claude Agents Used Self-Replicating Malware Amid Conflicting Goals
CVE (2)
Malware (11)
People (26)
Threat Actors (11)
MITRE ATT&CK (15)
Vendors (17)
Products (70)
Tools (19)
Industries (12)
Countries (4)
Note: Related entities, including threat actors, malware, CVEs, MITRE ATT&CK techniques, vendors, products, tools, countries, and industries, are shown when they appear in the same reporting. Their presence does not necessarily mean they were targeted, compromised, vulnerable, responsible for the activity, or directly involved in the incident.
