Vendor
Ggml-Org vulnerabilities
Updated . Rebuilt every hour.
Junglewise Threat Intelligence has tracked 12 vulnerabilities in Ggml-Org: 0 in the last 7 days and 9 in the last 90 days, 0 of them critical and 0 exploited in the wild. The most recent, CVE-2026-119052, was published on 29 October 2026. 9 vulnerabilities in the last four weeks, up from none in the four before. 2 technologies have a page of their own.
- Last 7 days
- 0
- Last 90 days
- 9
- Critical, all time
- 0
- Exploited in the wild
- 0
About Ggml-Org
An open-source organization focused on machine learning libraries and the GGML tensor format.
Ggml-Org technologies
Latest Ggml-Org vulnerabilities
- CVE-2026-119052: llama.cpp ggml-rpc server denial of servicehighCVSS 7.5
- CVE-2026-118375: llama.cpp out-of-bounds write in ggml-rpc RDMA transporthighCVSS 8.1
- CVE-2026-116829: llama.cpp integer overflow in gguf_init_from_readermediumCVSS 6.6
- CVE-2026-116816: llama.cpp heap out-of-bounds write in PLAMO2 tokenizerhighCVSS 7.8
- CVE-2025-71439: llama.cpp heap out-of-bounds read in tokenizer loadingmediumCVSS 5.5
- CVE-2024-58400: llama.cpp out-of-bounds read in decode/encode functionshighCVSS 8.2
- CVE-2024-58399: llama.cpp out-of-bounds read in llama_model_loadermediumCVSS 6.1
- CVE-2026-116467: ggml-org llama.cpp reachable assertion in Mirostat SamplermediumCVSS 5.3
- CVE-2026-116096: ggml-org llama.cpp out-of-bounds write in Pocket-TTSmediumCVSS 5.3
- CVE-2026-17513: ggml-org whisper.cpp reachable assertion in ggml_ftype_to_ggml_typelowCVSS 3.3
- CVE-2026-17512: ggml-org whisper.cpp out-of-bounds read in log_mel_spectrogramlowCVSS 3.3
- CVE-2026-10298: ggml-org whisper.cpp null pointer dereference in whisper_model_loadlowCVSS 3.3
Most severe Ggml-Org vulnerabilities
Exploited in the wild first, then by severity and CVSS score.
- CVE-2024-58400: llama.cpp out-of-bounds read in decode/encode functionshighCVSS 8.2
- CVE-2026-118375: llama.cpp out-of-bounds write in ggml-rpc RDMA transporthighCVSS 8.1
- CVE-2026-116816: llama.cpp heap out-of-bounds write in PLAMO2 tokenizerhighCVSS 7.8
- CVE-2026-119052: llama.cpp ggml-rpc server denial of servicehighCVSS 7.5
- CVE-2026-116829: llama.cpp integer overflow in gguf_init_from_readermediumCVSS 6.6
- CVE-2024-58399: llama.cpp out-of-bounds read in llama_model_loadermediumCVSS 6.1
- CVE-2025-71439: llama.cpp heap out-of-bounds read in tokenizer loadingmediumCVSS 5.5
- CVE-2026-116467: ggml-org llama.cpp reachable assertion in Mirostat SamplermediumCVSS 5.3
- CVE-2026-116096: ggml-org llama.cpp out-of-bounds write in Pocket-TTSmediumCVSS 5.3
- CVE-2026-17513: ggml-org whisper.cpp reachable assertion in ggml_ftype_to_ggml_typelowCVSS 3.3
Vulnerabilities per week
9 vulnerabilities in the last four weeks, up from none in the four before. The last 13 weeks, by the week each vulnerability was published.
| Week of | Bar | Vulns | Critical |
|---|---|---|---|
| 17 Aug 2026 | 0 | 0 | |
| 24 Aug 2026 | 0 | 0 | |
| 31 Aug 2026 | 0 | 0 | |
| 7 Sep 2026 | 0 | 0 | |
| 14 Sep 2026 | 0 | 0 | |
| 21 Sep 2026 | 0 | 0 | |
| 28 Sep 2026 | 0 | 0 | |
| 5 Oct 2026 | 0 | 0 | |
| 12 Oct 2026 | 0 | 0 | |
| 19 Oct 2026 | 1 | 0 | |
| 26 Oct 2026 | 8 | 0 | |
| 2 Nov 2026 | 0 | 0 | |
| 9 Nov 2026 | 0 | 0 |
Embed a badge
A live badge for a README, a status page or an internal wiki: how many Ggml-Org vulnerabilities were published in the last 7 days and how many of them are critical, refreshed hourly.
[](https://junglewise.ai/threats/vendors/ggml-org)<a href="https://junglewise.ai/threats/vendors/ggml-org"><img src="https://junglewise.ai/threats/vendors/ggml-org/badge.svg" alt="Ggml-Org vulnerabilities" /></a>How this is built
Junglewise Threat Intelligence collects vulnerabilities from NVD, GitHub Security Advisories, OSV, the CISA Known Exploited Vulnerabilities catalog, FIRST EPSS and vendor advisories, and matches each one to the technologies and vendors it affects. Dates are the date a vulnerability was published, in UTC.
The pages are rebuilt from the database every hour. Frozen weekly and monthly reports never change once published, so they can be cited.
Use this data
The same data is at https://junglewise.ai/threats/vendors/ggml-org.json, and this page as text at https://junglewise.ai/threats/vendors/ggml-org.md, for scripts and language models. It is free to reuse under CC BY 4.0 with a link back to this page.
Cite as: Junglewise Threat Intelligence, "Ggml-Org vulnerabilities", https://junglewise.ai/threats/vendors/ggml-org, 9 November 2026.