Out-of-bounds Write Affecting llama.cpp package, versions <7593+dfsg-1


Severity

Recommended
0.0
critical
0
10

Snyk's Security Team recommends NVD's CVSS assessment. Learn more

Threat Intelligence

EPSS
0.45% (37th percentile)

Do your applications use this vulnerable package?

In a few clicks we can analyze your entire application and see what components are vulnerable in your application, and suggest you quick fixes.

Test your applications
  • Snyk IDSNYK-DEBIAN14-LLAMACPP-16066071
  • published15 Apr 2026
  • disclosed8 Jan 2026

Introduced: 8 Jan 2026

CVE-2026-21869  (opens in a new tab)
CWE-787  (opens in a new tab)

How to fix?

Upgrade Debian:14 llama.cpp to version 7593+dfsg-1 or higher.

NVD Description

Note: Versions mentioned in the description apply only to the upstream llama.cpp package and not the llama.cpp package as distributed by Debian. See How to fix? for Debian:14 relevant fixed versions and status.

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 Base Scores

version 3.1