High severity · published Aug 12, 2024
CVE-2024-42477
llama.cpp global-buffer-overflow in ggml_type_size
7.5
CVSS
0.5%
EPSS
No
On KEV
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.
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Attack vector
Network
Complexity
Low
Privileges
None
User interaction
None
Confidentiality
None
Integrity
None
Availability
High
Scope
Unchanged
Exploitation
Is it being used?
Exploit prediction (EPSS)0.5% · higher than 40% of CVEs
Exploited in the wildNo evidence yet
CISA KEVNot listed
Ransomware campaign useNot known
Affected products
Which versions
LL
llama.cpp · ggerganov
< b3561 · source: vendor, NVD, CISA
References
NVD
https://nvd.nist.gov/vuln/detail/CVE-2024-42477
CVE.org
https://www.cve.org/CVERecord?id=CVE-2024-42477
Patch
https://github.com/ggerganov/llama.cpp/commit/b72942fac998672a79a1ae3c03b340f7e629980b
Vendor Advisory
https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-mqp6-7pv6-fqjf
More from llama.cpp
9.8
CVE-2024-42479
llama.cpp allows write-what-where in rpc_server::set_tensor
9.8
CVE-2024-42478
llama.cpp allows Arbitrary Address Read in rpc_server::get_tensor
9.8
CVE-2024-21825
A heap-based buffer overflow vulnerability exists in the GGUF library GGUF_TYPE_ARRAY/GGUF_TYPE_STRING parsing functionality of llama.cpp Commit 18c2e17
9.8
CVE-2024-23496
A heap-based buffer overflow vulnerability exists in the GGUF library gguf_fread_str functionality of llama.cpp Commit 18c2e17
9.8
CVE-2024-21836
A heap-based buffer overflow vulnerability exists in the GGUF library header.n_tensors functionality of llama.cpp Commit 18c2e17