CVE-2024-23496

CVE-2024-23496 affects llama.cpp’s GGUF file parsing in the gguf_fread_str function. The root cause is an integer overflow when reading a string length p->n, leading to p->data = calloc(p->n + 1, 1) and a potentially undersized allocation. A heap-based buffer overflow can occur when the ...

CVE-2024-23605

Affected: llama.cpp with GGUF header.n_kv parsing (commit 18c2e17). TALOS details a heap-based buffer overflow in gguf_init_from_file caused by allocating ctx->kv with header.n_kv, risking overflow when writing kv->key strings if header.n_kv overflows the allocation. Result: potential code ...

CVE-2024-21825

Talos details CVE-2024-21825 in llama.cpp (GGUF library) focusing on parsing of GGUF_TYPE_ARRAY/GGUF_TYPE_STRING within gguf_init_from_file. An attacker-provided .gguf file can trigger a heap-based buffer overflow when kv->value.arr.n is large, due to an integer overflow in the allocation kv-&...

CVE-2024-21836

CVE-2024-21836 affects llama.cpp (GGUF library header.n_tensors parsing). Talos reports a heap-based buffer overflow caused by an integer overflow when allocating ctx->infos for a crafted .gguf file, which can lead to a heap overflow during reading tensor names (info->name). Vulnerable comp...

CVE-2024-21802

Talos reports a heap-based buffer overflow in llama.cpp (Commit 18c2e17) related to the GGUF library info->ne parsing when processing .gguf files, which can lead to remote code execution. The vulnerability stems from writing beyond a 4-element info->ne array during gguf_init_from_file, with...

CVE-2024-42479

In llama.cpp, a vulnerability exists in the unsafe data pointer member of the rpc_tensor structure, enabling arbitrary address writes via rpc_server::set_tensor. The issue is a code-level flaw in LLM inference code paths written in C/C++, with a root cause tied to the data pointer in the rpc_tens...

CVE-2024-42478

CVE-2024-42478 concerns llama.cpp where an unsafe data pointer in the rpc_tensor structure can lead to arbitrary address reads. Several sources concur this is a code-level issue; the public CVE description states the vulnerability is fixed in b3561. Some connected advisories also advise upgrading...

CVE-2024-42477

CVE-2024-42477 affects llama.cpp (C/C++) where an unsafe type member in the rpc_tensor structure can trigger a global-buffer-overflow, potentially leaking memory data. The issue is reported as fixed in commit b3561 and is reflected in Fedora security advisory FEDORA-2024-89c69bb9d3 and related ad...

CVE-2024-41130

CVE-2024-41130 affects llama.cpp (C/C++) with a null pointer dereference in gguf_init_from_file. Root cause: null pointer dereference prior to version b3427. Impact: as documented, DoS-like behavior stemming from the crash/denial of service. Remediation: upgrade to version b3427 or later (per off...

CVE-2026-27940

Summary of CVE-2026-27940 : The llama.cpp component has a vulnerability in gguf_init_from_file_impl() within gguf.cpp where an integer overflow leads to an undersized heap allocation. This enables a subsequent fread() to write 528+ bytes of attacker-controlled data past the buffer boundary, const...

CVE-2025-49847

CVE-2025-49847 affects llama.cpp: prior to v5662, an attacker-supplied GGUF vocabulary can trigger a buffer overflow in the vocabulary-loading path. The root cause is in llama_vocab::impl::token_to_piece(), where a large size_t token length is cast to int32_t, bypassing the length check and causi...

CVE-2025-52566

CVE-2025-52566 affects llama.cpp (tokenizer in llama_vocab::tokenize). Prior to version b5721, a signed vs. unsigned integer overflow enables heap-overflow during tokenization, causing unintended behavior in token copying. This could enable heap-related issues during inference with crafted input....

CVE-2026-34159

The CVE-2026-34159 entry for llama.cpp describes an unauthenticated RCE via the RPC backend: prior to v.b8492, deserialize_tensor() omits bounds validation when tensor.buffer == 0, enabling an attacker to read/write arbitrary process memory through crafted GRAPH_COMPUTE messages. Combined with AL...

CVE-2026-33298

Summary (CVE-2026-33298) : llama.cpp (C/C++) contains an integer overflow in the ggml_nbytes function during GGUF tensor parsing, allowing an attacker to bypass memory validation by crafting tensor dimensions. This can cause ggml_nbytes to report a far too small size (examples cite 4 MB vs exabyt...