CVE-2026-21869
CRITICAL EPSS 35.1%
Published Jan 8, 20265mo ago · Modified Jun 17, 20262w ago
9.8 CVSS 3.1
Published Jan 8, 2026 5mo ago
Last Modified Jun 17, 2026 2w ago
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.
CVSS Details
Base Score
Exploitability
Impact
Vector string
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H Attack Vector Network
Attack Complexity Low
Privileges Required None
User Interaction None
Scope Unchanged
Confidentiality High
Integrity High
Availability High
Threat Intelligence
EPSS Exploit Probability
35.1% percentile
Exploit & Patch Status
Public Exploit Known
No Patch Available
Weaknesses 1
CWE-787 Out-of-bounds Write Memory Safety
Affected Products 1
| Vendor | Product | Version | Range |
|---|---|---|---|
| ggml | llama.cpp | * | any |
References 1
- github.com https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8947-pfff-2f3c
Remediation
No remediation data recorded yet
Check vendor advisories and the NVD entry for patch availability.