Vulnerability record · CVE-2024-42478 · published 12 August 2024
CVE-2024-42478: Ggml llama.cpp out-of-bounds read vulnerability
Ggml · Llama.Cpp
llama.cpp provides LLM inference in C/C++. The unsafe `data` pointer member in the `rpc_tensor` structure can cause arbitrary address reading. This vulnerability is fixed in b3561.
Description
llama.cpp provides LLM inference in C/C++. The unsafe `data` pointer member in the `rpc_tensor` structure can cause arbitrary address reading. This vulnerability is fixed in b3561.
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Affected products
1 vulnerable configurations from NVD's CPE data, grouped by vendor and product.
References
Track CVE-2024-42478 inside VULONE
Watch it alongside the ransomware crews, C2 infrastructure and forum chatter that reference it, query it through the API and pull it into your SIEM over TAXII.
Related vulnerabilities
Same products first, then exploited flaws of the same weakness class.
Source: NIST National Vulnerability Database (record CVE-2024-42478), CISA KEV, FIRST EPSS (scores of 2026-09-27). This page is refreshed as NVD updates the record.