Every CVESearch/Get API key

CVE-2024-42477

llama.cpp global-buffer-overflow in ggml_type_size

5.3 Medium

CVE-2024-42477 is a medium vulnerability (CVSS 5.3) in Ggerganov Llama.cpp, published August 12, 2024. No source lists public exploit code. EPSS puts the chance of exploitation in the next 30 days at 0.46%, the 40th percentile. No source names a fixed version.

What does this mean?
Severity
5.3 MediumCVSS 3.1, CVE List
Exploit chance
0.46%EPSS, 40th percentile
Exploitation
None knownNot on CISA’s or ENISA’s lists
Fixed in
No fix listedNo source names one

Description

llama.cpp provides LLM inference in C/C++. The unsafe type member in the rpc_tensor structure can cause global-buffer-overflow. This vulnerability may lead to memory data leakage. The vulnerability is fixed in b3561.

Attack profile

How easy it is to exploit

Attack vector
Network
Complexity
Low
Privileges needed
None
User interaction
None

What an attacker can affect

Confidentiality
Low
Integrity
None
Availability
None

Exploit likelihood

0.46%Up 0.4 points since Aug 13, 2024
90%50%10%1%

Affected products

What each source reports

CVE List Score used5.3

llama.cpp global-buffer-overflow in ggml_type_size

llama.cpp provides LLM inference in C/C++. The unsafe type member in the rpc_tensor structure can cause global-buffer-overflow. This vulnerability may lead to memory data leakage. The vulnerability is fixed in b3561.

Record
CVE-2024-42477
CVSS 3.1
5.3 MediumCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N
Weakness
CWE-125
Updated
2026-11-02
EUVDEUVD-2024-396375.3

llama.cpp provides LLM inference in C/C++. The unsafe type member in the rpc_tensor structure can cause global-buffer-overflow. This vulnerability may lead to memory data leakage. The vulnerability is fixed in b3561.

Record
EUVD-2024-39637
CVSS 3.1
5.3 MediumCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N
Updated
2026-11-03
NVD5.3

llama.cpp provides LLM inference in C/C++. The unsafe type member in the rpc_tensor structure can cause global-buffer-overflow. This vulnerability may lead to memory data leakage. The vulnerability is fixed in b3561.

Record
CVE-2024-42477
CVSS 3.1
5.3 MediumCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N
CVSS 3.1
7.5 HighCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Weakness
CWE-125, CWE-401
Updated
2026-11-02
OSV5.3

llama.cpp global-buffer-overflow in ggml_type_size

llama.cpp provides LLM inference in C/C++. The unsafe type member in the rpc_tensor structure can cause global-buffer-overflow. This vulnerability may lead to memory data leakage. The vulnerability is fixed in b3561.

Record
CVE-2024-42477
CVSS 3.1
5.3 MediumCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N
Weakness
CWE-125
Updated
2026-11-02

History

History
RecordedChangedSources
aliases, products, publishedEUVD
first indexedCVE List, NVD, OSV

Dates are when Every CVE recorded each change. Upstream dates may differ.

References

MoveEnter Open