Double Free in Ggml Llama.cpp
CVE-2026-43622
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.
Vulnerability class: Double Free
EPSS: 0.002 (5.1th percentile) — read the EPSS interpretation.
CVSS v3 metric
CVSS v3 base score 7.8 (High). Vector: CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H.
Affected products
- Ggml Llama.cpp
- Ggml-org Llama.cpp — versions b1886, 0.9.0, 5c0d18881e0e9794c96b2602736b758bac9d9388
Weakness classification (CWE)
References
- disclosure@vulncheck.com (release-notes, Patch, Release Notes, Vendor Advisory)
- disclosure@vulncheck.com (Patch, patch)
- disclosure@vulncheck.com (related, Patch, Third Party Advisory)
- disclosure@vulncheck.com (Patch, Third Party Advisory, third-party-advisory)
Frequently asked questions
- What is CVE-2026-43622?
- CVE-2026-43622 is a high-severity vulnerability in Ggml Llama.cpp, classified under Double Free. CVSS score: 7.8/10. Published 2026-08-06.
- How severe is CVE-2026-43622?
- High severity. CVSS v3 base score is 7.8 out of 10.