- CVSS
- HIGH · 7.8v3.1CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
- Published
- 2026-08-06
- Weakness
- CWE-415, CWE-762
- Source
- nvd.nist.gov/vuln/detail/CVE-2026-43622
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.
References
- https://github.com/Vladimir-tokarev-cyera/llama-cpp-security-patches
- https://github.com/ggml-org/llama.cpp/commit/5c0d18881e0e9794c96b2602736b758bac9d9388
- https://github.com/ggml-org/llama.cpp/releases/tag/b7446
- https://www.vulncheck.com/advisories/llama-cpp-b1886-b7445-double-free-via-llama-android-cpp
How GTK Cyber trains on this
AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2026-43622 fall into. Our hands-on courses are taught by Charles Givre and other practitioners who break and defend production AI systems.