CVE & CISA-KEV Catalog

CVE-2026-21869

HIGH
8.8
CVSS v3
NVD

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.

CWE-787Out-of-bounds Write

CVSS v3 Vector

Exploitability

Attack VectorNetwork
Attack ComplexityLow
Privileges RequiredNone
User InteractionRequired
ScopeUnchanged

Impact

ConfidentialityHigh
IntegrityHigh
AvailabilityHigh

CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

Exploit Intelligence

0.44%probability of exploitation in 30 days
35thpercentile

Low risk: more likely to be exploited than 35% of all known CVEs.

References

Find and fix vulnerabilities across your fleet

TridentStack Control continuously scans your Windows, macOS, and Linux fleet for known vulnerabilities, prioritizes them by severity and active exploitation, and patches them automatically.

Start free

This product uses NVD data but is not endorsed or certified by the NVD. EPSS scores courtesy of FIRST.org (https://www.first.org/epss). Source: CISA KEV Catalog. Data as of 2026-02-02.