llama.cpp through commit 97f06e9, when started with the --reranking flag, allows remote attackers to cause a denial of service (std::bad_alloc and HTTP 500) via a negative top_n value in a POST request to /rerank.
Vendor
ggml vulnerabilities
29 published CVES affecting ggml, from public sources (CVE.org, NVD, CISA KEV, FIRST EPSS, OSV).
- Total
- 29
- Critical
- 12
- High
- 14
- Medium
- 3
- Low
- 0
- Unscored
- 0
- CISA KEV
- 0
Products
Latest ggml CVEs
Newest publication first · page 1 of 2
-
HighCVSS 7.5 EPSS 0.59%
-
HighCVSS 7.5 EPSS 0.43%
llama.cpp b5693 and before has a Reachable Assertion via the gguf_reader::read function.
-
HighCVSS 7.5 EPSS 0.49%
llama.cpp b5693 and before is vulnerable to Uncontrolled Recursion in common/json-schema-to-grammar.cpp, resulting in a denial of service.
-
CriticalCVSS 9.2 EPSS 0.48%
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 access ctx_server.v...
-
CriticalCVSS 9.2 EPSS 0.57%
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 trigger the vulnerabil...
-
MediumCVSS 6.3 EPSS 0.50%
llama.cpp builds b4882 before b8487 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...
-
CriticalCVSS 9.2 EPSS 0.70%
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 directory to corrupt...
-
HighCVSS 8.5 EPSS 0.23%
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 INT32_MIN to the /v1...
-
HighCVSS 8.5 EPSS 0.20%
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 parameters to trigger...
-
HighCVSS 7.3 EPSS 0.24%
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_cont...
-
MediumCVSS 6.8 EPSS 0.19%
llama.cpp builds b1886 through b7445 contain a null pointer dereference vulnerability in the LLaMA-Android JNI wrapper where the bench_1model() function fails to validate the model context pointer before dereferencing it. Attackers can supply a malicious, corrupt, or truncated mo...
-
CVE-2026-70638 llama.cpp b1886–b7445 Integer Overflow via new_1batch() in llama-android.cpp
PublishedHighCVSS 8.5 EPSS 0.23%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 heap buffer allocatio...
-
HighCVSS 8.5 EPSS 0.23%
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. Attackers can trigger t...
-
CriticalCVSS 9.8 EPSS 1.6%
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 crafted GRAPH_COMPUT...
-
CVE-2026-33298 llama.cpp has a Heap Buffer Overflow via Integer Overflow in GGUF Tensor Parsing
PublishedHighCVSS 7.8 EPSS 0.51%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_nbytes to return a sign...
-
HighCVSS 7.8 EPSS 0.21%
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...
-
CriticalCVSS 9.8 EPSS 0.53%
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 value is supplied an...
-
HighCVSS 8.8 EPSS 0.36%
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 tokens copying size com...
-
HighCVSS 8.8 EPSS 0.55%
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: llama_vocab::impl::tok...
-
CriticalCVSS 9.8 EPSS 2.6%
llama.cpp provides LLM inference in C/C++. The unsafe data pointer member in the rpc_tensor structure can cause arbitrary address writing. This vulnerability is fixed in b3561.
-
CriticalCVSS 9.8 EPSS 0.60%
llama.cpp provides LLM inference in C/C++. The unsafe data pointer member in the rpc_tensor structure can cause arbitrary address reading. This vulnerability is fixed in b3561.
-
HighCVSS 7.5 EPSS 0.46%
llama.cpp provides LLM inference in C/C++. The unsafe type member in the rpc_tensor structure can cause global-buffer-overflow. This vulnerability may lead to memory data leakage. The vulnerability is fixed in b3561.
-
MediumCVSS 6.5 EPSS 0.34%
llama.cpp provides LLM inference in C/C++. Prior to b3427, llama.cpp contains a null pointer dereference in gguf_init_from_file. This vulnerability is fixed in b3427.
-
HighCVSS 8.8 EPSS 0.70%
Llama.cpp is LLM inference in C/C++. There is a use of uninitialized heap variable vulnerability in gguf_init_from_file, the code will free this uninitialized variable later. In a simple POC, it will directly cause a crash. If the file is carefully constructed, it may be possible...
-
CriticalCVSS 9.8 EPSS 1.3%
A heap-based buffer overflow vulnerability exists in the GGUF library GGUF_TYPE_ARRAY/GGUF_TYPE_STRING parsing functionality of llama.cpp Commit 18c2e17. A specially crafted .gguf file can lead to code execution. An attacker can provide a malicious file to trigger this vulnerabil...
Sources: CVE.org, NVD, CISA KEV, FIRST EPSS, OSV and public exploit-reference metadata. Product matching comes from the published CVE records. A proof-of-concept means public code exists; it is not evidence of exploitation.