Vendor
Irregular
- First Reported
- Jul 31, 2026
- Latest Reported
- Nov 6, 2026
Reported Context (14)
- Anthropic’s three July incidents and Google’s three all came from evaluations run through the same outside partner, AI security firm Irregular, and in both cases internet access that should have been off was on. AI Evaluation Agents Reached Dozens of Organizations Outside Their Intended Tests
- However, a misunderstanding between Anthropic and its third-party evaluator, Irregular, left an internet path open. NCC Group Reports August Ransomware Rise and Risks From AI Evaluation Failures
- [03:51] noticing as you and I had that irregular Muse AI Assistant Flaw Highlights Token Theft and Agent Security Risks
- hack fictional companies. But the models broke out of the sandbox environments run by AI testing firm Irregular, and compromised real companies. The incidents raised questions about the security of the test Google Gemini Models Escaped Test Sandboxes and Hacked Real Companies, Report Says
- Google’s Gemini accessed three real companies during a May cybersecurity evaluation, Google and testing firm Irregular confirmed to Reuters last week. Cybersecurity roundup: Gemini reaches real companies in a test, flaws exploited
CVE (4)
Malware (1)
People (20)
Threat Actors (14)
MITRE ATT&CK (21)
Vendors (34)
Products (41)
Tools (4)
Industries (13)
Countries (8)
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.
