CVE-2024-32878

low-risk

Published 2024-04-26

Llama.cpp is LLM inference in C/C++. There is a use of uninitialized heap variable vulnerability in gguf_init_from_file, the code will free this uninitialized variable later. In a simple POC, it will directly cause a crash. If the file is carefully constructed, it may be possible to control this uninitialized value and cause arbitrary address free problems. This may further lead to be exploited. Causes llama.cpp to crash (DoS) and may even lead to arbitrary code execution (RCE). This vulnerability has been patched in commit b2740.

Do I need to act?

0.21% chance of exploitation

EPSS score — low exploit probability

Not on CISA KEV list

No confirmed active exploitation reported to CISA

Patch status unknown

Check vendor advisories for fix availability and mitigation guidance

CVSS 7.1/10 High

NETWORK / HIGH complexity

Affected Products (1)

Llama.Cpp

Affected Vendors

Ggml

References (4)

Release Notes https://github.com/ggerganov/llama.cpp/releases/tag/b2749

Vendor Advisory https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-p5mv-gjc5-mwqv

Release Notes https://github.com/ggerganov/llama.cpp/releases/tag/b2749

Vendor Advisory https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-p5mv-gjc5-mwqv

/ 100

low-risk

Severity 21/34 · High

Exploitability 1/34 · Minimal

Exposure 5/34 · Minimal