Vulnerability · Published Aug 6, 2026 · Assigned by VulnCheck

CVE-2026-43629llama.cpp b4882–b9058 Buffer Overflow in KV Cache State Restore

High 8.1

In plain English

A high-severity out-of-bounds write in llama.cpp from ggml-org. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.7% (higher than 53% of all known vulnerabilities).

Severity (CVSS 3.1)8.1High

Exploit odds (30 days)0.7%top 46.7% of all CVEs

Exploited in the wildNo reportsCISA SSVC: none

Attack toolingNoneno public tooling known

Official 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 packages & fixed versions

Ecosystem	Package	Fixed in	Advisory
Debian:14	llama.cpp	no fix listed	DEBIAN-CVE-2026-43629
Ubuntu:26.04:LTS	llama.cpp	no fix listed	UBUNTU-CVE-2026-43629
Ubuntu:26.10	llama.cpp	no fix listed	UBUNTU-CVE-2026-43629

Affected products (as reported)

Vendor	Product	Versions
ggml-org	llama.cpp	b4882 – through b9058

Weakness: CWE-787, CWE-190 · Vector: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H

References

https://github.com/Vladimir-tokarev-cyera/llama-cpp-security-patches mitigation
https://www.vulncheck.com/advisories/llama-cpp-b4882-b9058-buffer-overflow-in-kv-cache-state-restore third-party-advisory