Is CVE-2026-17500 exploited in the wild?

No. Junglewise Threat Intelligence has no report of CVE-2026-17500 being exploited in the wild.

How severe is CVE-2026-17500?

Medium severity, with a CVSS score of 5.3, published 27 July 2026.

Which products and versions are affected?

GGML Llama.Cpp d006858, e15efe0.

Is there a fix for CVE-2026-17500?

No fixed version is recorded yet. Check the vendor's advisory in the references below. If you run it, Junglewise drafts a mitigation that fits your setup and applies it once you approve, with senior security engineers behind it.

How is CVE-2026-17500 attacked?

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

Am I affected by CVE-2026-17500?

Check whether you run GGML 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-2026-17500: ggml-org llama.cpp null pointer dereference in json-schema-to-grammar

CVE-2026-17500 · Severity: medium · CVSS 5.3 · Published 2026-07-27

A vulnerability exists in llama.cpp, a popular library used for running Large Language Models (LLMs). By providing a specially crafted JSON schema, a remote attacker can cause the software to crash. This results in a denial-of-service, potentially interrupting AI services or applications relying on this library for processing data.

Technologies: GGML Llama.Cpp. Vendors: GGML.

Quick answers

Is CVE-2026-17500 exploited in the wild?: No. Junglewise Threat Intelligence has no report of CVE-2026-17500 being exploited in the wild.
How severe is CVE-2026-17500?: Medium severity, with a CVSS score of 5.3, published 27 July 2026.
Which products and versions are affected?: GGML Llama.Cpp d006858, e15efe0.
Is there a fix for CVE-2026-17500?: No fixed version is recorded yet. Check the vendor's advisory in the references below. If you run it, Junglewise drafts a mitigation that fits your setup and applies it once you approve, with senior security engineers behind it.
How is CVE-2026-17500 attacked?: It is attacked over the network, in a software library.
Am I affected by CVE-2026-17500?: Check whether you run GGML 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.

Technical details

A vulnerability exists in the `_visit_pattern` function within `common/json-schema-to-grammar.cpp` of llama.cpp. The issue stems from improper validation of regex patterns during JSON-Schema to grammar conversion. Specifically, the code calls `seq.back()` without verifying if the vector is empty when handling quantifiers (e.g., *, +, ?, {n,m}) following unsupported regex constructs like lookarounds. Additionally, the `transform()` function lacks a recursion depth limit, leading to potential stack exhaustion. A remote attacker can exploit this by submitting a crafted JSON schema (e.g., via a `response_format` request to a server) to trigger a SIGSEGV or stack overflow, resulting in a process crash. A pull request (#25308) has been proposed to add null checks and nesting limits.

Affected products

ggml-org llama.cpp d006858, e15efe0

Timeline

2026-07-03: disclosed: Issue reported on GitHub repository
2026-07-04: other: Pull request #25308 submitted to fix the issue
2026-07-27: advisory: CVE-2026-17500 published

References

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