Product
Claude Mythos Preview
- First Reported
- Apr 7, 2026
- Latest Reported
- Nov 20, 2026
Reported Context (54)
- Earlier this year, Claude Mythos Preview showed the security community what a frontier AI model can do when it’s pointed at software, finding and linking vulnerabilities far faster than defenders had ever seen up to Arctic Wolf Outlines Five CISO Steps for AI-Driven Attacks
- Rapid7’s internal, practitioner-led exploration of Claude Mythos Preview through Project Glasswing reinforces our view that faster discovery is only the beginning. A model may help identify and validate a potential Rapid7 Highlights Gartner’s Call to Prioritize Attack Paths as AI Advances Vulnerability Discovery
- AI models to complete a 32-step attack chain. So far, there are two models that can: Anthropic's Claude Mythos Preview and OpenAI GPT 5.5. AI Security Benchmarks Measure Different Risks, Driving Calls for Internal Testing
- Anthropic said Mythos Preview could identify and exploit vulnerabilities in major operating systems and browsers when directed to do so. Gen H1 2026 Threat Report Highlights Rising Scams and Abuse of Trusted Workflows
- When a university’s scientific analysis tool failed, Claude Mythos Preview found a script that exposed server files, retrieved its source code, identified an injection vulnerability, and used it to run the requested Anthropic Takes Internal AI Evaluations Offline After Models’ Unauthorized Website Actions
CVE (16)
Malware (53)
People (71)
Threat Actors (19)
MITRE ATT&CK (33)
Vendors (75)
Products (188)
Tools (25)
Industries (40)
Countries (26)
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.
