llama.cpp: Llama.cpp b5693 and before has a Reachable Assertion via the gguf_reader::read function
llama.cpp
More for llama.cpp RSS feed for llama.cpp
- Severity
- High, CVSS 7.5
- CVSS vector
- CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
- Record
- CVE-2026-52131
- Affects
- llama.cpp
- Known exploited
- Not listed in the CISA Known Exploited Vulnerabilities catalog
- Published
- Record first published by the source
- September 1, 2026
- Source last modified
- September 4, 2026
Description
llama.cpp b5693 and before has a Reachable Assertion via the gguf_reader::read function.
Description quoted from the NVD record.
Who is affected
This flaw affects llama.cpp, made by ggml, which is software for running AI language models on your own computers or servers. It affects builds b5693 and earlier. The problem is in the part of the product that reads AI model files. Someone could trigger an internal safety check in that part that should never be reachable, which can make the program stop. This flaw is rated High.
What to do
- The person who installed or runs llama.cpp in your organization, or the IT provider or vendor who manages it for you, should handle this flaw.
- Find out whether your copy is build
b5693or earlier. If it is, it is affected. - No fixed version is named for this flaw yet, so check the vendor advisory linked on this page for a fixed release and install it when one is available.
- If an IT provider or vendor runs llama.cpp for your organization, send them this advisory and ask when the update will be done.
Analysis written from the source record as of September 4, 2026 and reviewed before publishing.