Vulnerability · Published Feb 26, 2024 · Assigned by talos
CVE-2024-21836
High 8.8
In plain English
A high-severity integer overflow in llama.cpp from llama.cpp. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 1.3% (higher than 71% of all known vulnerabilities).
Severity (CVSS 3.1)8.8High
Exploit odds (30 days)1.3%top 28.6% of all CVEs
Exploited in the wildNo reportsCISA SSVC: none
Attack toolingNoneno public tooling known
Official 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.
Affected products (as reported)
Weakness: CWE-190 · Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H