Advisory Database
  • Advisories
  • Dependency Scanning
  1. golang
  2. ›
  3. github.com/envoyproxy/ai-gateway
  4. ›
  5. GHSA-4gph-2hhr-5mwg

GHSA-4gph-2hhr-5mwg: Envoy AI Proxy - MCP Message Smuggling Vulnerability

May 19, 2026

Envoy AI Gateway was found to be affected by a protocol parser differential vulnerability due to improper implementation of the JSON-RPC 2.0 specification. Such differential causes a MCP message alteration, potentially causing a bypass of security controls in a multi-layered architecture.

According to the JSON RPC Spec used by Model Context Protocol, JSON RPC should be case sensitive https://www.jsonrpc.org/specification

[...]
All member names exchanged between the Client and the Server that are considered for matching of any kind should be considered to be case-sensitive. The terms function, method, and procedure can be assumed to be interchangeable.

The AI Gateway is accepting and processing case-variant fields that compliant MCP implementations correctly ignore. Crucially, Envoy does not just “pass through” the message by acting as a transparent proxy, it alters the traffic, allowing smuggling of unwanted requests.

The following steps represent the incoming message alteration:

  1. Incoming MCP Message:
{
id: 1,
jsonrpc: "2.0",
method: "tools/call",
params: {
name: "backend__greet",
Name: "backend__secretTool",
arguments: {
name: "World!"
},
Arguments: {
name: "Exploit"
}
}
}
  1. Parses the request, picking the non-standard Name field over the authorized name field due to internal case-insentitive parsing by libraries such as modelcontextprotocol/go-sdk/jsonrpc and github.com/bytedance/sonic
  2. Overwrites the authorized “backend__greet” value from the valid name field with the malicious value from the Name field
  3. Normalizes the injected “backend__secretTool” value (from the invalid Name field)
  4. Re-serializes the request into a new, valid MCP JRPC payload ({"name": "backend__secretTool"}) and forwards it upstream

This “smuggling” effect means Envoy actively transforms a request that might have been checked by any prior MCP-compliant implementation into a request that is valid and altered (from the perspective of the upstream backend), effectively introducing protocol modifications that may allow bypassing any prior authorization layer.

References

  • github.com/advisories/GHSA-4gph-2hhr-5mwg
  • github.com/envoyproxy/ai-gateway/security/advisories/GHSA-4gph-2hhr-5mwg

Code Behaviors & Features

Detect and mitigate GHSA-4gph-2hhr-5mwg with GitLab Dependency Scanning

Secure your software supply chain by verifying that all open source dependencies used in your projects contain no disclosed vulnerabilities. Dependency Scanning using SBOM also detects vulnerabilities from proprietary advisories that this site does not include. Learn more about Dependency Scanning using SBOM →

Affected versions

All versions before 0.6.0

Fixed versions

  • 0.6.0

Solution

Upgrade to version 0.6.0 or above.

Impact 3.7 LOW

CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:N

Learn more about CVSS

Weakness

  • CWE-178: Improper Handling of Case Sensitivity

Source file

go/github.com/envoyproxy/ai-gateway/GHSA-4gph-2hhr-5mwg.yml

Spotted a mistake? Edit the file on GitLab.

  • Site Repo
  • About GitLab
  • Terms
  • Privacy Statement
  • Contact

Page generated Sun, 08 Nov 2026 00:16:45 +0000.