CVE-2025-71439

MEDIUM
Published Oct 27, 2026 CWE-125

Description

llama.cpp before b5649 contains a heap out-of-bounds read vulnerability in llama_vocab::impl::print_info() that allows attackers to crash model loading via oversized special token IDs. Attackers can supply a crafted GGUF model with a short tokenizer.ggml.tokens array, causing llama-cli or llama-server to read past id_to_token and crash.

Is your site exposed to CVE-2025-71439?

Run a free security scan — no signup, results in seconds.

CVSS v3.1 Score

5.5
MEDIUM
CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H

Weakness Type (CWE)

CWE-125 Out-of-bounds Read

References

Frequently Asked Questions

What is CVE-2025-71439? +
llama.cpp before b5649 contains a heap out-of-bounds read vulnerability in llama_vocab::impl::print_info() that allows attackers to crash model loading via oversized special token IDs. Attackers can supply a crafted GGUF model with a short tokenizer.ggml.tokens array, causing llama-cli or llama-server to read past id_to_token and crash. It has a CVSS v3.1 base score of 5.5 (MEDIUM).
How severe is CVE-2025-71439? +
CVE-2025-71439 has a CVSS v3.1 score of 5.5 out of 10, rated MEDIUM. This is a medium-severity vulnerability that should be remediated as part of regular maintenance.
How do I check if I'm vulnerable to CVE-2025-71439? +
You can use Secably's free Website Scanner to check your website for known vulnerabilities. For infrastructure scanning, use the Port Scanner to identify exposed services that may be affected. Check the vendor advisories linked above for specific patch and version information.

Related Vulnerabilities

Don't wait for an exploit

Scan your website for vulnerabilities like CVE-2025-71439 — free, no signup required.