CVE-2026-43622
8.5
CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
Summary
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 Software
| Vendor | Product | Version Range | Status |
|---|---|---|---|
| ggml-org | llama.cpp | b1886 <= b7445 | affected |
| ggml-org | llama.cpp | 0.9.0 <= 0.17.1 | affected |
| ggml-org | llama.cpp | 5c0d18881e0e9794c96b2602736b758bac9d9388 | unaffected |
Weaknesses
- CWE-762: CWE-762 Mismatched Memory Management Routines
- CWE-415: CWE-415 Double Free
ADP Enrichment
CISA ADP Vulnrichment
- SSVC:
- Exploitation: none
- Automatable: no
- Technical Impact: total
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
Feedback
Was this page helpful?
Glad to hear it! Please tell us how we can improve.
Sorry to hear that. Please tell us how we can improve.