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.
References
Link | Resource |
---|---|
https://github.com/ggerganov/llama.cpp/commit/b72942fac998672a79a1ae3c03b340f7e629980b | Patch |
https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-5vm9-p64x-gqw9 | Exploit Vendor Advisory |
Configurations
History
15 Aug 2024, 14:03
Type | Values Removed | Values Added |
---|---|---|
CVSS |
v2 : v3 : |
v2 : unknown
v3 : 9.8 |
Summary |
|
|
First Time |
Ggerganov llama.cpp
Ggerganov |
|
References | () https://github.com/ggerganov/llama.cpp/commit/b72942fac998672a79a1ae3c03b340f7e629980b - Patch | |
References | () https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-5vm9-p64x-gqw9 - Exploit, Vendor Advisory | |
CPE | cpe:2.3:a:ggerganov:llama.cpp:*:*:*:*:*:*:*:* |
12 Aug 2024, 15:15
Type | Values Removed | Values Added |
---|---|---|
New CVE |
Information
Published : 2024-08-12 15:15
Updated : 2024-08-15 14:03
NVD link : CVE-2024-42478
Mitre link : CVE-2024-42478
CVE.ORG link : CVE-2024-42478
JSON object : View
Products Affected
ggerganov
- llama.cpp
CWE
CWE-125
Out-of-bounds Read