by Kastro
Paper/Archive/CVE-2026-43631

CVE-2026-43631

ggml-org llama.cpp — llama.cpp b7492–b9060 Use-After-Free RCE via llama-server

EPSS 0.6%CVSS 9.2
critical.is priorityof 100
37
CVSS 9.2 (CNA)9.2 / 10 × 3027.6Not in CISA KEV+300.0EPSS percentile 47.3.473 × 209.5No public exploit+100.0SSVC exploitation: none+100.0
Description · from the CVE record

llama.cpp builds b7492 through the latest b9060 contains a use-after-free vulnerability in the vocab pointer of llama-server when the --sleep-idle-seconds feature is enabled, allowing unauthenticated remote attackers to execute arbitrary code. Attackers can trigger the vulnerability by sending requests to affected endpoints while the server transitions to sleep mode, causing concurrent worker threads to dereference a freed vocab pointer that can be reclaimed with attacker-controlled data to achieve remote code execution.

Affected

ProductAffectedFixed inSource
llama.cppb7492 – b9060–CNA

Scores by source

VulnCheck (CNA)9.2CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
VulnCheck (CNA)8.1CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H
CISA ADPSSVCExploitation: none · Automatable: no · Technical impact: total

References

refgithub.com/Vladimir-tokarev-cyera/llama-cpp-security-patcheswriteupvulncheck.com/advisories/llama-cpp-b7492-b9060-use-after-free-rce-via-llama-server