Critical severity10.0NVD Advisory· Published Aug 12, 2024· Updated Apr 27, 2026

CVE-2024-42479

Description

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.

AI Insight

LLM-synthesized narrative grounded in this CVE's description and references.

Affected products

Ggml/Llama.cpp
cpe:2.3:a:ggml:llama.cpp:*:*:*:*:*:*:*:*
Range: <b3561
Ggerganov/Llama.cppllm-fuzzy

Patches

Vulnerability mechanics

References

github.com/ggerganov/llama.cpp/commit/b72942fac998672a79a1ae3c03b340f7e629980bnvdPatch
github.com/ggerganov/llama.cpp/security/advisories/GHSA-wcr5-566p-9cwjnvdExploitVendor Advisory

News mentions

No linked articles in our index yet.

cvss	0.650
epss	0.002
exploit	0.000
kev	0.000
patch	-0.070
ransomware	0.000