PT-2026-68726 · Llama.Cpp · Llama.Cpp
CVE-2026-43627
·
Published
2026-08-06
·
Updated
2026-08-08
CVSS v4.0
8.5
High
| Vector | AV:L/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X |
Name of the Vulnerable Software and Affected Versions
llama.cpp versions b1283 through b9058
Description
An integer overflow occurs in the
llama batch init() function when unchecked multiplications in malloc() calls wrap past INT32 MAX during allocation size calculations. An attacker can provide specially crafted parameters to trigger this overflow, leading to heap corruption. This may allow arbitrary code execution through batch operations that write beyond the allocated buffer boundaries.Recommendations
Update llama.cpp to a version later than b9058.
As a temporary mitigation, restrict the use of the
llama batch init() function with untrusted parameters.Fix
Integer Overflow
Found an issue in the description? Have something to add? Feel free to write us 👾
Related Identifiers
Affected Products
Llama.Cpp