CVE-2026-59207: n8n: "Allowed HTTP Request Domains" Restriction Bypass via AI Agents MCP Connector
Impact The AI Agents feature did not enforce the "Allowed HTTP Request Domains" restriction configured on credentials. As a result, a member-level user who had been granted use-only access to a shared credential could cause its secret to be sent to an external server they control, by pointing an MCP tool at an arbitrary URL and running the agent.
This issue only affects instances where the AI Agents module is enabled via N8NENABLEDMODULES=agents and at least one credential with domain restrictions has been shared with a member-level user.
Patches The issue has been fixed in n8n version 2.28.1 and 2.27.4. Users should upgrade to this version or later to remediate the vulnerability.
Workarounds If upgrading is not immediately possible, administrators should consider the following temporary mitigations: - Disable the AI Agents module by removing agents from the N8NENABLEDMODULES environment variable. - Restrict credential sharing to fully trusted users only. - Audit credentials with domain restrictions for unexpected sharing relationships.
These workarounds do not fully remediate the risk and should only be used as short-term mitigation measures.
Other sources
n8n is an open source workflow automation platform. Prior to 2.27.4 and 2.28.1, the AI Agents feature did not enforce the Allowed HTTP Request Domains restriction configured on credentials when an MCP tool was pointed at an arbitrary URL, allowing a member-level user with use-only access to a shared credential to send its secret to an external server they control. This issue is fixed in versions 2.27.4 and 2.28.1.
— NVD
Affected Software
Remediation
Recommended actions to resolve this vulnerability, in priority order.
- Upgrade
Upgrade
npm/n8nto a version that resolves this vulnerability.Fixed in 2.27.4 - Upgrade
Upgrade
npm/n8nto a version that resolves this vulnerability.Fixed in 2.28.1 - Upgrade
Upgrade
n8nto a version that resolves this vulnerability.Fixed in 2.27.4 - Upgrade
Upgrade
n8nto a version that resolves this vulnerability.Fixed in 2.28.1 - Configuration
Disable the AI Agents feature by removing `agents` from the `N8N_ENABLED_MODULES` environment variable (issue affects instances with `N8N_ENABLED_MODULES=agents`).
n8n AI Agents module N8N_ENABLED_MODULES = remove `agents` - Compensating control
Restrict credential sharing to fully trusted users only (member-level users with use-only access to shared credentials are the affected scenario when AI Agents is enabled).
- Operational
Audit credentials with domain restrictions for unexpected sharing relationships, especially where domain-restricted credentials have been shared with member-level users.
Event History
Frequently Asked Questions
What is the severity of CVE-2026-59207?
CVE-2026-59207 has a risk rating of 62, indicating a moderate severity level.
How do I fix CVE-2026-59207?
To fix CVE-2026-59207, upgrade your n8n installation to version 2.27.4 or 2.28.1 or later.
What systems are affected by CVE-2026-59207?
CVE-2026-59207 affects n8n versions prior to 2.27.4 and 2.28.1.
What type of vulnerability is CVE-2026-59207?
CVE-2026-59207 is a restriction bypass vulnerability related to the Allowed HTTP Request Domains.
Who is impacted by CVE-2026-59207?
This vulnerability potentially impacts users with member-level access who can utilize shared AI Agents.