10

CVE-2024-42479

Exploit

llama.cpp allows write-what-where in rpc_server::set_tensor

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.
Daten sind bereitgestellt durch National Vulnerability Database (NVD)
Ggml ≫ Llama.Cpp Version < b3561
Zu dieser CVE wurde keine Warnung gefunden.
EPSS Metriken
Typ Quelle Score Percentile
EPSS FIRST.org 2.63% 0.835
CVSS Metriken
Quelle Base Score Exploit Score Impact Score Vector String
nvd@nist.gov 9.8 3.9 5.9
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
security-advisories@github.com 10 3.9 6
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H
CWE-123 Write-what-where Condition

Any condition where the attacker has the ability to write an arbitrary value to an arbitrary location, often as the result of a buffer overflow.

CWE-787 Out-of-bounds Write

The product writes data past the end, or before the beginning, of the intended buffer.

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