UTC
Medium

MCP create_workflow_from_code Accepts Cross-Project Credentials When Auth Type Is an Expression

GHSA-vfrj-582q-mvcp · published 2026-08-05

Severity
Medium
CVSS score
5.3
Chance of exploitation (EPSS)
No CVE
Fixed in
2.34.1
What it is

The MCP create_workflow_from_code tool did not apply the same expression-awareness guard to credential validation that the runtime execution path uses. When a node's authentication type was set to an expression rather than a literal string, the credential-reference validator treated the raw expression as the active type, which never matched the real credential key. As a result, the cross-project ownership check was skipped and a credential belonging to another project could be persisted as a binding on a workflow in a different project. Exploitation requires MCP to be enabled on the instance, a valid MCP Bearer API key, and knowledge of a target credential ID from another project. …

What to do

Upgrade n8n to 2.34.1 or later. If you start it from an MCP config with npx or uvx, pin that version so an old cached copy is not used.

The issue has been fixed in n8n versions 2.33.4 and 2.34.1. Users should upgrade to one of these versions or later to remediate the vulnerability.

If you cannot upgrade yet

If upgrading is not immediately possible, administrators should consider the following temporary mitigations: Restrict n8n instance access to fully trusted users only. Disable MCP server access or revoke MCP API keys until the instance is patched. Audit workflows created via MCP for unexpected cross-project credential references. These workarounds do not fully remediate the risk and should only be used as short-term mitigation measures.

Affected
PackageRegistryAffectedFixed in
n8nnpm< 2.33.42.33.4
n8nnpm< 2.34.12.34.1

The impact, patch and workaround text comes from the advisory, shortened (published by n8n). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.

Sources: GitHub Advisory Database, reviewed and malware advisories (CC BY 4.0, https://github.com/advisories); advisories published by Cursor (https://github.com/cursor/cursor/security/advisories); advisories published by OpenClaw (https://github.com/openclaw/openclaw/security/advisories); advisories published by vLLM (https://github.com/vllm-project/vllm/security/advisories); advisories published by Open WebUI (https://github.com/open-webui/open-webui/security/advisories); advisories published by n8n (https://github.com/n8n-io/n8n/security/advisories); advisories published by Flowise (https://github.com/FlowiseAI/Flowise/security/advisories); advisories published by Langflow (https://github.com/langflow-ai/langflow/security/advisories); advisories published by the MCP Python SDK project (https://github.com/modelcontextprotocol/python-sdk/security/advisories); advisories published by MLflow (https://github.com/mlflow/mlflow/security/advisories); CISA Known Exploited Vulnerabilities catalog (CC0). Data as of 2026-11-22. ShieldMap describes how each problem works and how to fix it; it does not publish exploit code. Report a correction to [email protected].