CVE-2026-17501: ggml-org llama.cpp JSON-Schema-to-GBNF Conversion json-schema-to-grammar.cpp transform recursion

Published Jul 27, 2026
·
Updated

A flaw has been found in ggml-org llama.cpp e15efe0. This vulnerability affects the function transform of the file common/json-schema-to-grammar.cpp of the component JSON-Schema-to-GBNF Conversion. This manipulation causes uncontrolled recursion. The attack may be initiated remotely. The pull request to fix this issue awaits acceptance.

Affected Software

1 affected component
ggml-org llama.cpp=e15efe0

Event History

Jul 27, 2026
CVE Published
via MITRE·12:30 AM
Data Sourced
via MITRE·12:30 AM
DescriptionSeverityWeakness
Data Sourced
via NVD·01:16 AM
DescriptionSeverityWeakness
Mar 1, 58538
Event
via NVD·10:23 AM

Frequently Asked Questions

1

What is the severity of CVE-2026-17501?

The severity of CVE-2026-17501 is classified as medium with a score of 5.3.

2

What are the potential impacts of CVE-2026-17501?

CVE-2026-17501 could lead to resource allocation issues that can be exploited remotely.

3

How do I fix CVE-2026-17501?

To address CVE-2026-17501, it's recommended to update to the latest version of ggml-org llama.cpp that includes the fix for this vulnerability.

4

Who is affected by CVE-2026-17501?

CVE-2026-17501 affects users of the ggml-org llama.cpp software, specifically those using the JSON-Schema-to-GBNF Conversion functionality.

5

Can CVE-2026-17501 be exploited remotely?

Yes, CVE-2026-17501 can be exploited remotely, making it crucial for affected users to implement the necessary updates.

Contact

SecAlerts Pty Ltd.
132 Wickham Terrace
Fortitude Valley,
QLD 4006, Australia
info@secalerts.co
By using SecAlerts services, you agree to our services end-user license agreement. This website is safeguarded by reCAPTCHA and governed by the Google Privacy Policy and Terms of Service. All names, logos, and brands of products are owned by their respective owners, and any usage of these names, logos, and brands for identification purposes only does not imply endorsement. If you possess any content that requires removal, please get in touch with us.
© 2026 SecAlerts Pty Ltd.
ABN: 70 645 966 203, ACN: 645 966 203