llama.cpp builds b1886 through b7445 contain a race condition use-after-free vulnerability in the LLaMA-Android JNI wrapper where bench_1model() and free_1context() lack synchronization, allowing Thread A to operate on freed memory while Thread B concurrently frees the llama_context. Attackers can exploit this by performing heap spray with attacker-controlled data containing a fake vtable to hijack the vtable pointer at offset +0x30, causing llama_batch_allocr::clear() to dereference arbitrary memory and achieve remote code execution.
Attack Parameters
Attack Vector
Local
Requires local access
Attack Complexity
High
Difficult to exploit
Attack Requirements
None
No additional conditions
Privileges Required
None
No privileges needed
User Interaction
Passive
Minimal interaction
Impact Assessment
Confidentiality
High
Complete data leak
Integrity
High
Complete data modification
Availability
High
Complete denial of service
CVSS Vector v4.0
Weakness Type (CWE)
Vulnerable Products
ggml-org:llama.cpp
References 4
https://github.com/Vladimir-tokarev-cyera/llama-cpp-security-patches
disclosure@vulncheck.com
https://github.com/ggml-org/llama.cpp/commit/5c0d18881e0e9794c96b2602736b758bac…
disclosure@vulncheck.com
https://github.com/ggml-org/llama.cpp/releases/tag/b7446
disclosure@vulncheck.com
https://www.vulncheck.com/advisories/llama-cpp-b1886-b7445-race-condition-use-a…
disclosure@vulncheck.com