CVE-2024-42477: medium-severity vulnerability in ggerganov llama.cpp
llama.cpp global-buffer-overflow in ggml_type_size
Published · Updated
E-mail alert when it lands in KEV, gets a public PoC or its score goes up.
13Vexday Risk Score
No sign of exploitation. No public exploitation artifact known so far.
ssvc Trackcvss 5.3epss 0.5%
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:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N
Affected products
ggerganov · llama.cppRelated CVEs — ggerganov llama.cpp
In the same product, most dangerous first.
CVE-2024-42479CRITICALllama.cpp allows write-what-where in rpc_server::set_tensorEPSS 2.6%CVE-2024-32878HIGH Use of Uninitialized Variable Vulnerability in llama.cppEPSS 0.7%CVE-2024-42478MEDIUMllama.cpp allows Arbitrary Address Read in rpc_server::get_tensorEPSS 0.6%CVE-2024-41130MEDIUMllama.cpp null pointer dereference in gguf_init_from_fileEPSS 0.3%