Description
llama.cpp builds b4882 through b9058 contain a heap buffer overflow vulnerability in the KV cache state restore path where the state_read_data() function computes write size without overflow checking, allowing attackers with write access to the slot_save_path directory to corrupt heap memory. Attackers can craft malicious state files where cell_count multiplication overflows or exceeds tensor buffer allocation to write attacker-controlled bytes past buffer boundaries, potentially resulting in heap metadata corruption, model weight corruption, or arbitrary code execution via function pointer overwrite.
Affected products
ggml: llama.cpp
References2
- github.com/Vladimir-tokarev-cyera/llama-cpp-security-patches PatchThird Party Advisory
- www.vulncheck.com/advisories/llama-cpp-b4882-b9058-buffer-overf… MitigationPatchThird Party Advisory
Metrics
- CVSS 3.1
-
8.1
HIGH
Score source: CNA
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H - CVSS 4.0
-
9.2
CRITICAL
Score source: CNA
CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/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 - EPSS — exploit probability
- 1% percentile: 54 · as of 12 November 2026
- CWE
- CWE-190CWE-787
Could this be exploited in your environment?
A patch closes the known hole. A penetration test shows what an attacker can still reach — with proof.