# CVE-2026-96437: Kong Gateway Enterprise ai-azure-content-safety plugin bypass

Source: https://junglewise.ai/threats/cve-2026-96437-the-ai-azure-content-safety-plugin-in-kong-gateway-enterprise  
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-2026-96437 · Severity: info · Published 2026-11-10

Kong Gateway Enterprise includes a security plugin that scans API requests for harmful content before they reach backend services. This vulnerability allows attackers to bypass those safety checks by sending requests larger than the plugin's buffer, potentially allowing malicious prompts to reach AI models without inspection.

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

## Quick answers

**Is CVE-2026-96437 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-96437 being exploited in the wild.

**How severe is CVE-2026-96437?** Informational severity, published 10 November 2026.

**Which products and versions are affected?** Kong Gateway Enterprise <UNKNOWN>.

**Is there a fix for CVE-2026-96437?** 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-2026-96437 attacked?** It is attacked over the network, in a hosted service.

**Am I affected by CVE-2026-96437?** Check whether you run Kong Gateway Enterprise 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

The ai-azure-content-safety plugin in Kong Gateway Enterprise fails to inspect request bodies that exceed its in-memory buffer size, allowing large payloads to bypass content-safety scanning. This is a logic flaw in the plugin's request handling that can be exploited by sending oversized request bodies. An attacker with network access to Kong Gateway can craft requests larger than the buffer to evade content checks.

## Affected products

- Kong Gateway Enterprise <UNKNOWN>

## Timeline

- 2026-11-10: disclosed

## References

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

## Related threats

- [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)
- [Kong Gateway Enterprise and Kong AI Gateway HTTP header injection via X-Forwarded-Prefix](https://junglewise.ai/threats/cve-2026-92441-kong-gateway-enterprise-and-kong-ai-gateway-include-decoded-cr-lf)
- [Kong Gateway Enterprise SAML plugin audience restriction bypass](https://junglewise.ai/threats/cve-2026-92439-the-saml-plugin-in-kong-gateway-enterprise-does-not-enforce)