CVE-2026-43630 llama.cpp b5702–b7653 Out-of-Bounds Read Information Disclosure

llama.cpp builds b5702 through b7653 contain an out-of-bounds read vulnerability in the recurrent memory state restore path that allows attackers with write access to the slot save directory to read memory past the end of the allocated cells array. Attackers can craft a malicious slot file with a...

CVE-2026-43629 llama.cpp b4882–b9058 Buffer Overflow in KV Cache State Restore

llama.cpp builds b4882 through b9058 contain a heap buffer overflow vulnerability in the KV cache state restore path where the statereaddata function computes write size without overflow checking, allowing attackers with write access to the slotsavepath directory to corrupt heap memory. Attackers...

CVE-2026-43629

llama.cpp builds b4882 through b9058 contain a heap buffer overflow vulnerability in the KV cache state restore path where the statereaddata function computes write size without overflow checking, allowing attackers with write access to the slotsavepath directory to corrupt heap memory. Attackers...

CVE-2026-43627 llama.cpp b1283–b9058 Integer Overflow in llama_batch_init() Function

llama.cpp builds b1283 through b9058 contain an integer overflow vulnerability in the llamabatchinit function where unchecked multiplications in malloc calls can wrap past INT32MAX when computing allocation sizes. Attackers can pass specially crafted parameters to trigger integer overflow, causin...

CVE-2026-43627

The CVE-2026-43627 issue affects llama.cpp (b1283–b9058) in the llama_batch_init() function, where unchecked multiplications in malloc() cause allocation sizes to wrap past INT32_MAX. This leads to heap corruption and can potentially enable arbitrary code execution through subsequent batch operat...

CVE-2026-70639 llama.cpp b1886–b7445 Null Pointer Dereference DoS via llama-android.cpp

llama.cpp builds b1886 through b7445 contain a null pointer dereference vulnerability in the LLaMA-Android JNI wrapper where the bench1model function fails to validate the model context pointer before dereferencing it. Attackers can supply a malicious, corrupt, or truncated model file to trigger ...

CVE-2026-43622

CVE-2026-43622 affects llama.cpp builds b1886–b7445, where the LLaMA-Android JNI wrapper presents a double free vulnerability. The code allocates memory with malloc() in new_1batch() but frees it with the C++ delete operator in free_1batch(), leading to heap metadata corruption. Consequences desc...

CVE-2026-17501

A flaw has been found in ggml-org llama.cpp e15efe0. This vulnerability affects the function transform of the file common/json-schema-to-grammar.cpp of the component JSON-Schema-to-GBNF Conversion. This manipulation causes uncontrolled recursion. The attack may be initiated remotely. The pull...

Linux Distros Unpatched Vulnerability : CVE-2026-34159

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - llama.cpp is an inference of several LLM models in C/C++. Prior to version b8492, the RPC backend's deserializetensor skips all bounds validation when a tensor'...

EUVD-2026-17975

llama.cpp is an inference of several LLM models in C/C++. Prior to version b8492, the RPC backend's deserializetensor skips all bounds validation when a tensor's buffer field is 0. An unauthenticated attacker can read and write arbitrary process memory via crafted GRAPHCOMPUTE messages. Combined...

PT-2026-29570

Name of the Vulnerable Software and Affected Versions llama.cpp versions prior to b8492 Description A logic bug in the RPC backend's deserialize tensor function allows an unauthenticated attacker to read and write arbitrary process memory. This occurs because bounds validation is skipped when a...

Linux Distros Unpatched Vulnerability : CVE-2026-33298

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - llama.cpp is an inference of several LLM models in C/C++. Prior to b7824, an integer overflow vulnerability in the ggmlnbytes function allows an attacker to...

Linux Distros Unpatched Vulnerability : CVE-2026-27940

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - llama.cpp is an inference of several LLM models in C/C++. Prior to b8146, the ggufinitfromfileimpl in gguf.cpp is vulnerable to an Integer overflow, leading to ...

CVE-2026-27940 llama.cpp has a Heap Buffer Overflow via Integer Overflow in `mem_size` Calculation — Bypass of CVE-2025-53630 Fix

llama.cpp is an inference of several LLM models in C/C++. Prior to b8146, the ggufinitfromfileimpl in gguf.cpp is vulnerable to an Integer overflow, leading to an undersized heap allocation. Using the subsequent fread writes 528+ bytes of attacker-controlled data past the buffer boundary. This is...

PT-2026-24951

llama.cpp is an inference of several LLM models in C/C++. Prior to b8146, the gguf init from file impl in gguf.cpp is vulnerable to an Integer overflow, leading to an undersized heap allocation. Using the subsequent fread writes 528+ bytes of attacker-controlled data past the buffer boundary. Thi...

llama.cpp 输入验证错误漏洞

Llama.cpp is a multimodal model developed by Georgi Gerganov. Prior versions of llama.cpp b8146 contained an input validation vulnerability; this vulnerability stemmed from an integer overflow in the ggufinitfromfileimpl function, which could lead to writing outside the buffer boundaries...

PT-2026-6804

Name of the Vulnerable Software and Affected Versions ggml-org llama.cpp versions prior to 55abc39 Description A flaw exists in the GBNF Grammar Handler component of ggml-org llama.cpp. Specifically, the llama grammar advance stack function within the llama.cpp/src/llama-grammar.cpp file is...

llama.cpp 安全漏洞

Llama.cpp is a multimodal model developed by Georgi Gerganov. Versions of Llama.cpp with the version number 55abc39 and earlier contain security vulnerabilities, which stem from a stack buffer overflow in the GBNF syntax processor...

CVE-2026-21869

CVE-2026-21869 affects llama.cpp prior to commit 55d4206c9, where the server’s completion endpoints parse the non‑negative constraint for the JSON input parameter n_discard without validation. A negative n_discard can cause a reversed range/offset in llama_memory_seq_rm/add, leading to out‑of‑bou...

CVE-2026-21869 llama.cpp has Out-of-bounds Write in llama-server

llama.cpp is an inference of several LLM models in C/C++. In commits 55d4206c8 and prior, the ndiscard parameter is parsed directly from JSON input in the llama.cpp server's completion endpoints without validation to ensure it's non-negative. When a negative value is supplied and the context fill...