Ggml Llama.Cpp
CVE-2026-43628
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/completions or /v1/chat/completions endpoints. Attackers can exploit this vulnerability to crash the server with SIGSEGV causing denial of service for all connected users, or corrupt token sampling probabilities by reading garbage values from memory before the allocated buffer.
What this means for your business
- It affects Ggml Llama.Cpp. It matters if your company, or a supplier that handles your data, runs it.
- An attacker can use it only with access to the machine itself, without a login, but only after tricking someone into an action such as opening a file or a link.
- FIRST's prediction model gives it a 0.2% chance of attack attempts being seen in the next 30 days, ranking above 10% of all known flaws.
What to do
- 1Check whether your company or your suppliers run Ggml Llama.Cpp, and which version. The affected versions are listed further down this page.
- 2If you do, apply the vendor's fix. A patch or vendor advisory has been published.
Not sure if your company is exposed?
Fastnexa’s certified penetration testers can check whether attackers could use this flaw, or others like it, against your websites, apps and network. The full test is free for our first 10 founding clients until 31 December 2026.
Scoring
- CVSS
- 7.8 (v3.1)
- Vector
CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H- CVSS v4
- 8.5
- Weakness
- CWE-125
- Assigned by
- disclosure@vulncheck.com
Dates
- Published
- 2026-08-06
- Last modified
- 2026-09-21
- Sources
- NVD
Affected products
- Ggml Llama.Cppb3978 - b9058
As listed in the NVD configuration data. Not a statement about your estate.