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-2026-4156: ChargePoint Home Flex OCPP getpreq Stack-based Buffer Overflow Remote Code Execution Vulnerability. HIGH
- CVE-2026-40150: PraisonAIAgents is a multi-agent teams system. Prior to 1.5.128, the web_crawl() function in praison HIGH
- CVE-2025-58913: Improper Control of Filename for Include/Require Statement in PHP Program ('PHP Remote File Inclusio HIGH
- CVE-2026-40198: Net::CIDR::Lite versions before 0.23 for Perl does not validate IPv6 group count, which may allow IP MEDIUM
- CVE-2026-40188: goshs is Missing Write Protection for Parametric Data Values HIGH
Related Coverage
Threat Actors