First Apple M5 memory exploit discovered using Anthropic AI, gives root access on MacOS Claude Mythos helps security researchers bypass Memory Integrity Enforcement
News Source : Tom's Hardware UK
News Summary
- The vulnerability is simple in practice: run a command as a standard user and gain root (administrator) access to the machine.
- The exploit chain impressively sneaks past MIE, a security feature present on M5 and A19 chips that labels each 16-byte memory slice with a 4-bit tag associated with the pointers that use it.
- MIE is enforced at the hardware level in a hypervisor-like configuration and effectively protects against most common classes of security exploits, namely buffer overflows and use-after-free vulnerabilities.
Thanks to AIassisted security research, hackers with hats of various colors are finding exploits everywhere.
Never miss a story from us, subscribe to our newsletter