Ggml-org vulnerabilities
We track 21 vulnerabilities in Ggml-org products. 21 are rated high or critical, and none are known to be exploited. The most recent was published on October 29, 2026.
Latest Ggml-org vulnerabilities
- 7.5 High severity
llama.cpp: Uncaught Exception
llama.cpp b2877 before b11935 contains an uncaught exception vulnerability in the ggml-rpc server that allows unauthenticated remote attackers to crash the rpc-server by sending oversized message lengths. After the HELLO handshake, attackers can send a command
- 8.1 High severity
llama.cpp: Out-of-bounds Write
llama.cpp b8841 before b11865 contains an out-of-bounds write vulnerability in the ggml-rpc RDMA transport rdma_recv() function that allows unauthenticated peers to overflow the rpc-server stack. Attackers advertising RDMA capabilities in the HELLO message can
- 7.8 High severity
llama.cpp: Improper Validation of Array Index
llama.cpp b5899 before b10261 contains a heap out-of-bounds write vulnerability in llm_tokenizer_plamo2::build that allows attackers to corrupt heap memory via crafted GGUF models. Attackers can supply BYTE-typed token text like <0x-1> whose negative parsed va
- 8.2 High severity
llama.cpp: Improper Validation of Array Index
llama.cpp before b3701 contains an out-of-bounds read vulnerability in llama_decode_internal and llama_encode_internal that allows remote unauthenticated attackers to read memory by supplying unvalidated token IDs. Attackers can send integer-array prompts to t
- 8.1 High severity
llama.cpp: Use After Free
llama.cpp before b11393 contains a use-after-free and double free vulnerability in common_chat_peg_mapper::map that allows unauthenticated remote attackers to corrupt heap memory via a dangling current_tool pointer. Attackers can submit a chat_parser in a POST
- 7.3 High severity
A vulnerability was found in ggml-org llama.cpp bec4772f6.
A vulnerability was found in ggml-org llama.cpp bec4772f6. The impacted element is the function deserialize_tensor of the file ggml/src/ggml-rpc/ggml-rpc.cpp of the component ggml-RPC Server. Performing a manipulation of the argument op/op_params results in de
- 7.0 High severity
llama.cpp: Concurrent Execution using Shared Resource with Improper Synchronization
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
- 7.8 High severity
llama.cpp: Heap-based Buffer Overflow
llama.cpp builds b1886 through b7445 contain an integer overflow vulnerability in the LLaMA-Android JNI wrapper where the new_1batch() function multiplies sizeof(llama_seq_id) by an attacker-controlled n_seq_max parameter without overflow validation, causing h
- 8.1 High severity
llama.cpp: Time-of-check Time-of-use (TOCTOU) Race Condition
llama.cpp builds b7492 through the latest b9060 contains a use-after-free vulnerability in llama-server affecting six tokenization endpoints (/tokenize, /detokenize, /infill, /apply-template, /rerank, and /anthropic/count_tokens) that bypass the task queue and
- 8.1 High severity
llama.cpp: Concurrent Execution using Shared Resource with Improper Synchronization
llama.cpp builds b7492 through the latest b9060 contains a use-after-free vulnerability in the vocab pointer of llama-server when the --sleep-idle-seconds feature is enabled, allowing unauthenticated remote attackers to execute arbitrary code. Attackers can tr
- 8.1 High severity
llama.cpp: Integer Overflow or Wraparound
llama.cpp builds b4882 through b9058 contain a heap buffer overflow vulnerability in the KV cache state restore path where the state_read_data() function computes write size without overflow checking, allowing attackers with write access to the slot_save_path
- 7.8 High severity
llama.cpp: Out-of-bounds Read
llama.cpp builds b3978 through b9058 contain an integer underflow and out-of-bounds read vulnerability in the DRY sampler that allows unauthenticated attackers to trigger a heap buffer underflow by sending a crafted HTTP request with dry_allowed_length set to
- 7.8 High severity
llama.cpp: Integer Overflow or Wraparound
llama.cpp builds b1283 through b9058 contain an integer overflow vulnerability in the llama_batch_init() function where unchecked multiplications in malloc() calls can wrap past INT32_MAX when computing allocation sizes. Attackers can pass specially crafted pa
- 7.8 High severity
llama.cpp: Double Free
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. Att
- 9.8 Critical severity
llama.cpp: Improper Restriction of Operations within the Bounds of a Memory Buffer
llama.cpp is an inference of several LLM models in C/C++. Prior to version b8492, the RPC backend's deserialize_tensor() skips all bounds validation when a tensor's buffer field is 0. An unauthenticated attacker can read and write arbitrary process memory via
- 7.8 High severity
llama.cpp: Heap-based Buffer Overflow
llama.cpp is an inference of several LLM models in C/C++. Prior to b7824, an integer overflow vulnerability in the `ggml_nbytes` function allows an attacker to bypass memory validation by crafting a GGUF file with specific tensor dimensions. This causes `ggml_
- 7.8 High severity
llama.cpp: Heap-based Buffer Overflow
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-cont
- 9.8 Critical severity
llama.cpp: Out-of-bounds Write
llama.cpp is an inference of several LLM models in C/C++. In commits 55d4206c8 and prior, the n_discard 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
- 8.9 High severity
llama.cpp: Heap-based Buffer Overflow
llama.cpp is an inference of several LLM models in C/C++. Integer Overflow in the gguf_init_from_file_impl function in ggml/src/gguf.cpp can lead to Heap Out-of-Bounds Read/Write. This vulnerability is fixed in commit 26a48ad699d50b6268900062661bd22f3e792579.
- 8.8 High severity
llama.cpp: Improper Restriction of Operations within the Bounds of a Memory Buffer
llama.cpp is an inference of several LLM models in C/C++. Prior to version b5721, there is a signed vs. unsigned integer overflow in llama.cpp's tokenizer implementation (llama_vocab::tokenize) (src/llama-vocab.cpp:3036) resulting in unintended behavior in tok
- 8.8 High severity
llama.cpp: Improper Restriction of Operations within the Bounds of a Memory Buffer
llama.cpp is an inference of several LLM models in C/C++. Prior to version b5662, an attacker‐supplied GGUF model vocabulary can trigger a buffer overflow in llama.cpp’s vocabulary‐loading code. Specifically, the helper _try_copy in llama.cpp/src/vocab.cpp: ll