CVE-2026-21869

HIGH
2026-01-08 [email protected]
8.8
CVSS 3.1
Share

CVSS Vector

CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Attack Vector
Network
Attack Complexity
Low
Privileges Required
None
User Interaction
Required
Scope
Unchanged
Confidentiality
High
Integrity
High
Availability
High

Lifecycle Timeline

3
Analysis Generated
Mar 12, 2026 - 21:54 vuln.today
PoC Detected
Feb 02, 2026 - 19:12 vuln.today
Public exploit code
CVE Published
Jan 08, 2026 - 00:16 nvd
HIGH 8.8

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.

Analysis

Llama.cpp server endpoints fail to validate the n_discard parameter from JSON input, allowing negative values that trigger out-of-bounds memory writes when the context buffer fills. This memory corruption vulnerability affects LLM inference operations and can be exploited remotely without authentication to crash the service or achieve code execution; public exploit code exists and no patch is currently available.

Sign in for full analysis, threat intelligence, and remediation guidance.

Remediation

Within 7 days: Identify all affected systems running commits 55d4206c8 and and apply vendor patches promptly. If patching is delayed, consider network segmentation to limit exposure.

Sign in for detailed remediation steps.

Priority Score

64
Low Medium High Critical
KEV: 0
EPSS: +0.3
CVSS: +44
POC: +20

Vendor Status

Share

CVE-2026-21869 vulnerability details – vuln.today

This site uses cookies essential for authentication and security. No tracking or analytics cookies are used. Privacy Policy