UTC
Medium

FastMCP has a Command Injection vulnerability - Gemini CLI

CVE-2025-64340 · GHSA-m8x7-r2rg-vh5g · published 2026-03-31 · updated 2026-04-06

Severity
Medium
CVSS score
6.7
Chance of exploitation (EPSS)
0.75%
Fixed in
3.2.0
  • Exploitation Public proof of concept
  • Automatable No
  • Technical impact Total
  • CISA SSVC
What it is

Server names containing shell metacharacters (e.g., &) can cause command injection on Windows when passed to fastmcp install claude-code or fastmcp install gemini-cli. These install paths use subprocess.run() with a list argument, but on Windows the target CLIs often resolve to .cmd wrappers that are executed through cmd.exe, which interprets metacharacters in the flattened command string.

What to do

Upgrade fastmcp to 3.2.0 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.

Affected
PackageRegistryAffectedFixed in
fastmcpPyPI< 3.2.03.2.0
Downstream in the Official MCP Registry

47 registered MCP servers install an affected version today, by the dependency versions a fresh install resolves.

  • aws.api.us-east-1.ecs-mcp/serverfastmcp@2.14.0
  • aws.api.us-east-1.eks-mcp/serverfastmcp@2.14.0
  • io.github.aadeshrao123/unreal-mcpfastmcp@2.14.7
  • io.github.aahl/mcp-aktoolsfastmcp@2.14.7
  • io.github.aahl/mcp-notifyfastmcp@2.14.7
  • io.github.aahl/mcp-vodsfastmcp@2.14.7
  • io.github.ai-mcpower/mcpower-proxyfastmcp@2.13.0.2
  • io.github.alex-feel/mcp-context-serverfastmcp@3.1.0
  • io.github.ameyxd/petromcpfastmcp@2.14.7
  • io.github.andreasd083/amazing-marvin-complete-mcpfastmcp@2.14.7
  • io.github.ariffazil/arifos-mcpfastmcp@3.0.1
  • io.github.aws/aws-mcpfastmcp@2.14.0
All 47 servers on the trace →

The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). 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].