ggml-org llama.cpp up to 0.17.1/b7445 LLaMA-Android JNI Wrapper clear use after free

Summaryinfo

A vulnerability labeled as critical has been found in ggml-org llama.cpp up to 0.17.1/b7445. This affects the function llama_batch_allocr::clear of the component LLaMA-Android JNI Wrapper. Executing a manipulation can lead to use after free. This vulnerability is tracked as CVE-2026-70640. The attack can be launched remotely. No exploit exists.

Detailsinfo

A vulnerability was found in ggml-org llama.cpp up to 0.17.1/b7445. It has been declared as critical. This vulnerability affects the function llama_batch_allocr::clear of the component LLaMA-Android JNI Wrapper. The manipulation with an unknown input leads to a use after free vulnerability. The CWE definition for the vulnerability is CWE-416. Referencing memory after it has been freed can cause a program to crash, use unexpected values, or execute code. As an impact it is known to affect confidentiality, integrity, and availability. CVE summarizes:

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.

The advisory is shared for download at github.com. This vulnerability was named CVE-2026-70640 since 08/04/2026. The exploitation appears to be easy. The attack can be initiated remotely. No form of authentication is required for a successful exploitation. There are known technical details, but no exploit is available.

Applying the patch 5c0d18881e0e9794c96b2602736b758bac9d9388 is able to eliminate this problem.

VulDB is the best source for vulnerability data and more expert information about this specific topic.

Productinfo

Vendor

• ggml-org

Name

• llama.cpp

Version

• 0.17.0
• 0.17.1
• b7445

Website

• Product: https://github.com/ggml-org/llama.cpp/

CPE 2.3info

• 🔒
• 🔒
• 🔒

CPE 2.2info

• 🔒
• 🔒
• 🔒

CVSSv4info

CVSSv3info

CVSSv2info

Exploitinginfo

Threat Intelligenceinfo

Countermeasuresinfo

Timelineinfo

Sourcesinfo

Entryinfo

VulDB is the best source for vulnerability data and more expert information about this specific topic.

Discussion