CVE-2026-110178 · AI agents & MCP
NO FIX YET · SEE WHAT TO DO
A user with a team-scoped admin.import permission can use the bulk import endpoint to overwrite the URL, headers and credentials of public tools, resources and prompts owned by other tenants. Later gateway calls to those tools are then sent to an attacker-controlled host.
first public Nov 13, 2026 · 1 source
Check it with your coding agent
It reads this page and tells you if your code or app is affected.
Teams running IBM ContextForge MCP Gateway versions 1.0.0 through 1.0.11 in a multi-tenant setup, where some users hold team-scoped admin.import rights. Single-tenant deployments with no such users are less exposed. The sources do not describe default configuration.
Not affected if no-admin-import-users, single-tenant
Who cares ibm-contextforge, mcp, self-hosted
1.0.0 through 1.0.11.admin.import permission.1.0.11 (the sources do not name the fixed version).IBM ContextForge MCP Gateway 1.0.0 through 1.0.11 is vulnerable to improper access control in the bulk import path. A remote authenticated attacker holding a team-scoped admin.import permission can overwrite the endpoint URL, request headers, and authentication credentials of public tools, resources, and prompts owned by other tenants by sending a crafted POST request to /v1/import with conflict_strategy=update, redirecting subsequent AI gateway invocations to an attacker-controlled host.
This page as .md · .json · CVSS:3.1/AV:N/AC:L/PR:H/UI:N/S:C/C:N/I:L/A:N
NVD data is provided by NIST and is public domain. Posts quoted belong to their authors.
Are you affected?
Ask from here. InfraStack checks the affected versions against your stack and answers in your inbox.
InfraStack checks the affected versions against your stack and answers in Slack, with the evidence and the fix.
InfraStack checks it against your stack and answers on your report, with the evidence and the fix.