# CVE-2026-92544: Kong Gateway SQL injection in LLM usage counters

Source: https://junglewise.ai/threats/cve-2026-92544-sql-injection-in-the-llm-usage-counters-of-kong-gateway  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-11-10. Updated: 2026-11-10  
License: CC BY 4.0 with a link back

CVE-2026-92544 · Severity: info · Published 2026-11-10

Kong Gateway Enterprise and Kong AI Gateway are API management platforms that route and secure API traffic. A SQL injection vulnerability in the LLM usage counters feature allows an attacker to execute arbitrary SQL queries against the Kong database by crafting a malicious model name, potentially exposing or modifying sensitive data.

Technologies: [Kong AI Gateway](https://junglewise.ai/threats/technologies/kong-ai-gateway), [Kong Gateway Enterprise](https://junglewise.ai/threats/technologies/gateway-enterprise). Vendors: [Kong](https://junglewise.ai/threats/vendors/kong).

## Quick answers

**Is CVE-2026-92544 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-92544 being exploited in the wild.

**How severe is CVE-2026-92544?** Informational severity, published 10 November 2026.

**Which products and versions are affected?** Kong Gateway Enterprise; Kong AI Gateway.

**Is there a fix for CVE-2026-92544?** 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-2026-92544 attacked?** It is attacked over the network.

**Am I affected by CVE-2026-92544?** Check whether you run Kong AI Gateway or Kong Gateway Enterprise. 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

SQL injection vulnerability exists in the LLM usage counters component of Kong Gateway Enterprise and Kong AI Gateway, where user-supplied model names are not properly sanitized before being used in SQL queries. An unauthenticated or authenticated client can exploit this by sending a crafted model name to execute arbitrary SQL commands against the Kong database, gaining unauthorized access to or modification of data.

## Affected products

- Kong Gateway Enterprise
- Kong AI Gateway

## Timeline

- 2026-11-10: disclosed

## References

- [https://developer.konghq.com/ai-gateway/changelog/](https://developer.konghq.com/ai-gateway/changelog/)
- [https://developer.konghq.com/gateway/changelog/](https://developer.konghq.com/gateway/changelog/)

## Related threats

- [Kong Gateway Enterprise ai-azure-content-safety plugin bypass](https://junglewise.ai/threats/cve-2026-96437-the-ai-azure-content-safety-plugin-in-kong-gateway-enterprise)
- [Kong Gateway Enterprise cache key injection via separator characters](https://junglewise.ai/threats/cve-2026-92558-the-proxy-cache-and-proxy-cache-advanced-plugins-in-kong-gateway)
- [Kong Gateway Enterprise cache key omission vulnerability](https://junglewise.ai/threats/cve-2026-92545-the-proxy-cache-and-proxy-cache-advanced-plugins-in-kong-gateway)
- [Kong Gateway Enterprise cache poisoning via Authorization header](https://junglewise.ai/threats/cve-2026-92443-the-caching-plugins-in-kong-gateway-enterprise-and-kong-ai)
- [Kong Gateway Enterprise graphql-proxy-cache-advanced cache key bypass](https://junglewise.ai/threats/cve-2026-92442-the-graphql-proxy-cache-advanced-plugin-in-kong-gateway)