Description (CNA)
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.
Affected (CNA)
| Vendor / product | Versions |
|---|---|
| ggml-org / llama.cpp | affected b1886 through b7445; affected 0.9.0 through 0.17.1; unaffected 5c0d18881e0e9794c96b2602736b758bac9d9388 |
CWE
CWE-762, CWE-415
References
- https://github.com/ggml-org/llama.cpp/releases/tag/b7446
- https://github.com/ggml-org/llama.cpp/commit/5c0d18881e0e9794c96b2602736b758bac9d9388
- https://github.com/Vladimir-tokarev-cyera/llama-cpp-security-patches
- https://www.vulncheck.com/advisories/llama-cpp-b1886-b7445-double-free-via-llama-android-cpp
ADP enrichment
No English description supplied.
No references supplied.