CRITICAL: CVE-2024-42479 (CVSS 10) — ggml llama.cpp

CVE: CVE-2024-42479

CVSS: 10 (3.1) — CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H

Severity: CRITICAL

Status: Critical advisory

Affected

ggml llama.cpp

Summary

llama.cpp provides LLM inference in C/C++. The unsafe data pointer member in the rpc_tensor structure can cause arbitrary address writing. This vulnerability is fixed in b3561.

Verified Sources

References

https://github.com/ggerganov/llama.cpp/commit/b72942fac998672a79a1ae3c03b340f7e629980b
https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-wcr5-566p-9cwj

_Validated by the Lyrie Threat Intelligence Pipeline — 3 independent sources confirmed before publication. No speculation._

Lyrie Verdict

A vulnerability of this severity is exactly what Lyrie's anti-rogue-AI defense is built for: continuous, autonomous monitoring that doesn't wait for human reaction time.

#ggml #critical