CVE-2026-43629: llama.cpp builds b4882 through b9058 contain a heap buffer overflow vulnerability in the KV cache state restore path…
CVE-2026-43629 · Severity: high · CVSS 8.1 · Published 2026-08-06
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.
No. Junglewise Threat Intelligence has no report of CVE-2026-43629 being exploited in the wild.
How severe is CVE-2026-43629?
High severity, with a CVSS score of 8.1, published 6 August 2026.
Which products and versions are affected?
GGML Llama.Cpp. The advisory does not name versions.
Is there a fix for CVE-2026-43629?
No fixed version is recorded yet. Check the vendor's advisory in the references below. If you run it, Junglewise drafts a mitigation that fits your setup and applies it once you approve, with senior security engineers behind it.
Am I affected by CVE-2026-43629?
Check whether you run GGML Llama.Cpp. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.