Monitor vulnerabilities like this one. Sign up free to get alerted when software you use is affected.
4.9

Agentgateway: Malicious Input Can Contaminate API Requests

CVE-2026-29791 GHSA-v2x6-wwfw-r2rq GHSA-v2x6-wwfw-r2rq
Summary

If you use Agentgateway's MCP to OpenAPI conversion feature, a malicious input could potentially inject extra information into your API requests. This could allow an attacker to access unauthorized data or perform other unauthorized actions. To fix this issue, update to Agentgateway version 0.12.0 or later.

What to do
  • Update github.com agentgateway to version 0.12.0.
  • Update agentgateway github.com/agentgateway/agentgateway to version 0.12.0.
Affected software
VendorProductAffected versionsFix available
github.com agentgateway <= 0.12.0 0.12.0
agentgateway github.com/agentgateway/agentgateway <= 0.12.0 0.12.0
Original title
Agentgateway is missing parameter sanitization in MCP to OpenAPI conversion
Original description
### Summary

When converting MCP `tools/call` request to OpenAPI request, input path, query, and header values are not sanitized.

### Details

When using the [MCP to OpenAPI](https://agentgateway.dev/docs/standalone/latest/mcp/connect/openapi/) feature, the proxy lacks proper sanitization of input parameters in the MCP call, allowing:
* Injection of additional path or query parameters.
* Injection of additional headers.

### Impacted Versions

This vulnerability is fixed in Agentgateway v0.12.0+. Users on older versions are recommended to upgrade to v0.12.0+.

This feature only impacts usage of the [MCP to OpenAPI](https://agentgateway.dev/docs/standalone/latest/mcp/connect/openapi/) feature

### Credits

Agentgateway extends its thanks to @spacewander for the report!
nvd CVSS3.1 4.9
Vulnerability type
CWE-20 Improper Input Validation
Published: 5 Mar 2026 · Updated: 12 Mar 2026 · First seen: 6 Mar 2026