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.
References (2)
Core 2
Core References
Exploit, Vendor Advisory x_refsource_confirm
https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-wcr5-566p-9cwj
Scores
CVSS v3
10.0
EPSS
0.0568
EPSS Percentile
90.4%
Attack Vector
NETWORK
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H
CISA SSVC
Vulnrichment
Exploitation
poc
Automatable
no
Technical Impact
total
Details
CWE
CWE-123
CWE-787
Status
published
Products (2)
ggerganov/llama.cpp
< b3561
ggml/llama.cpp
< b3561
Published
Aug 12, 2024
Tracked Since
Feb 18, 2026