Is CVE-2024-58400 exploited in the wild?

No. Junglewise Threat Intelligence has no report of CVE-2024-58400 being exploited in the wild.

How severe is CVE-2024-58400?

High severity, with a CVSS score of 8.2, published 27 October 2026.

Which products and versions are affected?

Ggml-Org Llama.Cpp before b3701.

Is there a fix for CVE-2024-58400?

Yes: fixed in b3701 or later (commit eae5971 and related). Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.

How is CVE-2024-58400 attacked?

It is attacked over the network, in a software library.

Am I affected by CVE-2024-58400?

Check whether you run Ggml-Org Llama.Cpp at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

CVE-2024-58400: llama.cpp out-of-bounds read in decode/encode functions

CVE-2024-58400 · Severity: high · CVSS 8.2 · Published 2026-10-27

llama.cpp is a language model inference library used to run AI models locally. An unauthenticated attacker can send specially crafted requests to the llama-server endpoint with invalid token IDs, causing the server to read memory outside intended bounds. This can leak sensitive data from memory or crash the service.

Technologies: Ggml-Org Llama.Cpp. Vendors: Ggml-Org.

Quick answers

Is CVE-2024-58400 exploited in the wild?: No. Junglewise Threat Intelligence has no report of CVE-2024-58400 being exploited in the wild.
How severe is CVE-2024-58400?: High severity, with a CVSS score of 8.2, published 27 October 2026.
Which products and versions are affected?: Ggml-Org Llama.Cpp before b3701.
Is there a fix for CVE-2024-58400?: Yes: fixed in b3701 or later (commit eae5971 and related). Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.
How is CVE-2024-58400 attacked?: It is attacked over the network, in a software library.
Am I affected by CVE-2024-58400?: Check whether you run Ggml-Org Llama.Cpp at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

How to fix

Fixed in: b3701 or later (commit eae5971 and related)

Technical details

An out-of-bounds read vulnerability exists in llama_decode_internal and llama_encode_internal functions due to insufficient validation of token ID values. The functions fail to check that token IDs fall within the valid range (0 to n_vocab), allowing attackers to read arbitrary embedding memory via the /completion endpoint by supplying integer-array prompts with IDs outside valid bounds.

Affected products

ggml-org llama.cpp before b3701

Timeline

2026-10-27: disclosed

References

This page as Markdown. Free to reuse under CC BY 4.0 with a link back.