CVE-2026-29791 Agentgateway: Missing parameter sanitization in MCP to OpenAPI conversion
Attackers can exploit unsanitized MCP inputs during OpenAPI conversion to potentially execute code or bypass security controls in Agentgateway.
- Exploited in the wild
- Not known
- Login needed
- Any signed-in user
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- Available
What is CVE-2026-29791?
CVE-2026-29791 is a medium-severity vulnerability in agentgateway, published on 6 Mar 2026. Any signed-in user can exploit it over the network, with no action from the victim.
Official description
Agentgateway is an open source data plane for agentic AI connectivity within or across any agent framework or environment. Prior to version 0.12.0, when converting MCP tools/call request to OpenAPI request, input path, query, and header values are not sanitized. This issue has been patched in version 0.12.0.
Weakness: CWE-20
Which versions are affected by CVE-2026-29791?
2 open source packages ship an affected version, including github.com/agentgateway/agentgateway. It affects 1 product.
| Package | Affected | Fixed in |
|---|---|---|
github.com/agentgateway/agentgateway Go | All versions | 0.12.0 |
github.com/agentgateway/agentgateway Go | All versions | 0.12.0 |
Products include Lfprojects Agentgateway.
How do I fix CVE-2026-29791?
Upgrade github.com/agentgateway/agentgateway to 0.12.0 or later.
Is CVE-2026-29791 being exploited?
There is no known exploitation of CVE-2026-29791 in the wild and no public exploit code.
Sources
Also known as GHSA-v2x6-wwfw-r2rq.