Approved changes feed: RSS · Atom

cpe:2.3:a:ggerganov:llama.cpp:*:*:*:*:*:*:*:*

part: a version: * update: *

VendorGgerganov (7626e8d1-5237-5322-a345-86f100ad1d42)
ProductLlama.Cpp (489ef0a9-937d-5521-897f-16e0a3cbf577)
Edition*
Language*
Software edition*
Target software*
Target hardware*
Other*

Notes

Imported from purl2cpe mapping

PURL mappings

PURLSourceLast updated
pkg:github/ggerganov/llama.cpp purl2cpe 2026-06-01 10:14:40.079961

Vulnerability references

IdentifiercpeApplicabilitySubmitteddb.gcve.eu detailsRationale
CVE:CVE-2024-42479 vulnerable 2026-06-08 06:45:46.523212 llama.cpp allows write-what-where in rpc_server::set_tensor
CRITICAL (10)
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.
Published: 2024-08-12T15:07:19.150Z
Updated: 2024-08-13T13:47:10.838Z
Reference links
Imported from gcve-enriched-dumps CVE data
CVE:CVE-2024-42478 vulnerable 2026-06-08 06:45:46.522685 llama.cpp allows Arbitrary Address Read in rpc_server::get_tensor
MEDIUM (5.3)
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.
Published: 2024-08-12T15:05:12.697Z
Updated: 2024-08-16T19:15:15.749Z
Reference links
Imported from gcve-enriched-dumps CVE data
CVE:CVE-2024-42477 vulnerable 2026-06-08 06:45:46.521231 llama.cpp global-buffer-overflow in ggml_type_size
MEDIUM (5.3)
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.
Published: 2024-08-12T15:02:40.980Z
Updated: 2024-08-13T14:07:30.334Z
Reference links
Imported from gcve-enriched-dumps CVE data
CVE:CVE-2024-41130 vulnerable 2026-06-08 06:43:54.039630 llama.cpp null pointer dereference in gguf_init_from_file
MEDIUM (5.4)
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.
Published: 2024-07-22T17:28:47.708Z
Updated: 2024-08-02T04:46:51.141Z
Reference links
Imported from gcve-enriched-dumps CVE data
CVE:CVE-2024-32878 vulnerable 2026-06-08 06:37:24.633502 Use of Uninitialized Variable Vulnerability in llama.cpp
HIGH (7.1)
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 to control this uninitialized value and cause arbitrary address free problems. This may further lead to be exploited. Causes llama.cpp to crash (DoS) and may even lead to arbitrary code execution (RCE). This vulnerability has been patched in commit b2740.
Published: 2024-04-26T20:31:53.813Z
Updated: 2024-08-02T02:20:35.603Z
Reference links
Imported from gcve-enriched-dumps CVE data
CVE:CVE-2024-23605 vulnerable 2026-06-08 06:29:39.994527 db.gcve.eu details were skipped to keep the page responsive. Imported from gcve-enriched-dumps CVE data
CVE:CVE-2024-23496 vulnerable 2026-06-08 06:29:39.821055 db.gcve.eu details were skipped to keep the page responsive. Imported from gcve-enriched-dumps CVE data
CVE:CVE-2024-21836 vulnerable 2026-06-08 06:27:36.764742 db.gcve.eu details were skipped to keep the page responsive. Imported from gcve-enriched-dumps CVE data
CVE:CVE-2024-21825 vulnerable 2026-06-08 06:27:36.744265 db.gcve.eu details were skipped to keep the page responsive. Imported from gcve-enriched-dumps CVE data

Contribute

You can submit an edit proposal for this CPE entry or suggest a related product/vendor addition using the action button above.

Inspect record JSON

Open JSON directly

Open this panel to browse, search, copy or download the JSON record.