CVE detail

CVE-2024-21836 — CVE-2024-21836

Published 2024-02-26 · Modified 2026-06-17 · Vendor ggml · Product llama.cpp · Source nvd

HIGH

severity

CVSS-derived band

8.8

CVSS v3

0–10 scale

0.0135

EPSS probability

exploitation probability, 30d

69.0%

EPSS percentile

percentile vs all CVEs

NOT LISTED

CISA KEV

known exploited catalog

Description

A heap-based buffer overflow vulnerability exists in the GGUF library header.n_tensors functionality of llama.cpp Commit 18c2e17. A specially crafted .gguf file can lead to code execution. An attacker can provide a malicious file to trigger this vulnerability.

Remediation

No vendor-published fix data in our corpus for this CVE. Check the references below or the vendor's PSIRT / security advisories page.

References

cvedb.io · NVD · CISA KEV · FIRST EPSS · vendor advisories (CVE Program List v5). Informational only, no warranty — verify every remediation against the vendor advisory before acting on it. This product uses data from the NVD API but is not endorsed or certified by the NVD, CISA, FIRST.org or any vendor named. CVE® is a registered trademark of The MITRE Corporation.