HIGH

CVE-2026-43622

Ggml Llama.cpp 2026-08-06 CVSS v3.1

CVSS

7.8

Description

llama.cpp builds b1886 through b7445 contain a double free vulnerability in the LLaMA-Android JNI wrapper where new_1batch() allocates memory using malloc() while free_1batch() deallocates it using the C++ delete operator, causing heap metadata corruption. Attackers can trigger this memory management mismatch to cause denial of service through process crashes or potentially achieve arbitrary code execution depending on allocator state.

Weakness (CWE)

CWE-415 Double Free

CWE-762

EPSS Score

0.16%

Probability of exploitation in next 30 days

5.1th percentile

References

https://github.com/Vladimir-tokarev-cyera/llama-cpp-security-patches Patch, Third Party Advisory https://github.com/ggml-org/llama.cpp/commit/5c0d18881e0e9794c96b2602736b758bac9d9388 Patch https://github.com/ggml-org/llama.cpp/releases/tag/b7446 Patch, Release Notes, Vendor Advisory https://www.vulncheck.com/advisories/llama-cpp-b1886-b7445-double-free-via-llama-android-cpp Patch, Third Party Advisory

View on dbcve.org

Base CVE data derived from NVD (public domain). Enrichment by dbcve.org (CC-BY-4.0). Fetched via API.

Back to CVE