CVE-2026-21869
llama.cpp has Out-of-bounds Write in llama-server
Description
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 and the context fills up, llama_memory_seq_rm/add receives a reversed range and negative offset, causing out-of-bounds memory writes in the token evaluation loop. This deterministic memory corruption can crash the process or enable remote code execution (RCE). There is no fix at the time of publication.
INFO
Published Date :
Jan. 8, 2026, 12:16 a.m.
Last Modified :
Jan. 8, 2026, 8:15 p.m.
Remotely Exploit :
Yes !
Source :
[email protected]
CVSS Scores
| Score | Version | Severity | Vector | Exploitability Score | Impact Score | Source |
|---|---|---|---|---|---|---|
| CVSS 3.1 | HIGH | [email protected] |
Solution
- Update llama.cpp to validate n_discard JSON input.
- Ensure n_discard is non-negative before processing.
- Review memory management in token evaluation loop.
- Apply relevant security patches.
References to Advisories, Solutions, and Tools
Here, you will find a curated list of external links that provide in-depth
information, practical solutions, and valuable tools related to
CVE-2026-21869.
| URL | Resource |
|---|---|
| https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8947-pfff-2f3c | |
| https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8947-pfff-2f3c |
CWE - Common Weakness Enumeration
While CVE identifies
specific instances of vulnerabilities, CWE categorizes the common flaws or
weaknesses that can lead to vulnerabilities. CVE-2026-21869 is
associated with the following CWEs:
Common Attack Pattern Enumeration and Classification (CAPEC)
Common Attack Pattern Enumeration and Classification
(CAPEC)
stores attack patterns, which are descriptions of the common attributes and
approaches employed by adversaries to exploit the CVE-2026-21869
weaknesses.
We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).
Results are limited to the first 15 repositories due to potential performance issues.
The following list is the news that have been mention
CVE-2026-21869 vulnerability anywhere in the article.
The following table lists the changes that have been made to the
CVE-2026-21869 vulnerability over time.
Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.
-
CVE Modified by 134c704f-9b21-4f2e-91b3-4a467353bcc0
Jan. 08, 2026
Action Type Old Value New Value Added Reference https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8947-pfff-2f3c -
New CVE Received by [email protected]
Jan. 08, 2026
Action Type Old Value New Value Added Description 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 and the context fills up, llama_memory_seq_rm/add receives a reversed range and negative offset, causing out-of-bounds memory writes in the token evaluation loop. This deterministic memory corruption can crash the process or enable remote code execution (RCE). There is no fix at the time of publication. Added CVSS V3.1 AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H Added CWE CWE-787 Added Reference https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8947-pfff-2f3c