Skip to main content
When Detect identifies shadow servers or skills, follow this response framework to assess risk and take appropriate action.

Triage by Risk Level

Shadow MCP Servers

Risk LevelIndicatorsResponse
CriticalUnknown/suspicious source, broad permissions, external data exfiltration endpointsImmediate removal, incident response, credential rotation
HighThird-party MCP not in catalog, access to sensitive dataBlock via MDM, require security review before approval
MediumKnown vendor but not approved, limited scopeUser education, migrate to Runlayer-managed version
LowKnown safe MCP, read-only access, internal onlyDocument and monitor, encourage migration to Runlayer

Shadow Skills

Risk LevelIndicatorsResponse
HighRisky instructions detected — prompt injection, data exfiltration patterns, unsafe automationImmediate removal, investigate source repository
MediumPotentially risky characteristics that warrant reviewSecurity review, verify skill source and intent
LowMinor concerns, unlikely to pose a threatMonitor, encourage migration to managed skill
MinimalNo concerning patterns detectedDocument and track

Investigation Checklist

  1. Identify the user and their role
  2. Determine when the MCP or skill was configured/installed
  3. Review the stated purpose and actual capabilities
  4. Check if the MCP connects to external endpoints
  5. Assess what data the MCP or skill could access
  • Is it from a known vendor (GitHub, Slack, etc.)?
  • Is it an open-source project? Check repository activity and maintainers
  • Is it internally developed? Verify with the development team
  • Are there any known vulnerabilities or security advisories?
  • Is the skill from a trusted, known repository?
  • Does the skill contain instructions that could manipulate AI behavior (prompt injection)?
  • Does the skill instruct the AI to send data to external endpoints?
  • Is the skill a community skill or internally developed?
  • Does the skill’s scope match the user’s legitimate needs?
  • Does the user have a legitimate business reason?
  • Could an existing Runlayer-managed MCP or skill fulfill the need?
  • Is this a one-off or widespread usage pattern?
  • Migrate: Help user set up equivalent Runlayer-managed MCP or skill
  • Approve: Submit for formal review and add to catalog
  • Remove: Use MDM to remove configuration from device
  • Block: Add to blocklist if risky or prohibited

Response Workflow

Security Dashboard

Monitor security events and shadow alerts

Security Best Practices

Comprehensive MCP security guidelines and threat prevention

Audit Logs

View detailed activity logs for investigations

Admin Handbook

Complete administrator guide including approval workflows