Can Anthropic Keep Its Exploit-Writing AI Out of the Wrong Hands?
Its Mythos Preview model, which can allegedly find and exploit critical zero-days, also comes with certain controls, the vendor said.
Related Vulnerabilities
- CVE-2026-5392: Heap out-of-bounds read in PKCS7 parsing. A crafted PKCS7 message can trigger an OOB read on the hea LOW
- CVE-2026-40225: In udev in systemd before 260, local root execution can occur via malicious hardware devices and uns MEDIUM
- CVE-2026-33118: Microsoft Edge (Chromium-based) Spoofing Vulnerability MEDIUM
- CVE-2026-35041: fast-jwt has a ReDoS when using RegExp in allowed* leading to CPU exhaustion during token verificati MEDIUM
- CVE-2026-40178: ajenti.plugin.core has race conditions in 2FA MEDIUM
Related Coverage
Threat Actors