fastmcp-integration
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill configures and connects to external FastMCP Cloud MCP servers (mcp_servers URLs like https://your-server.fastmcp.app/mcp and catsmcp.fastmcp.app) and ingests their system messages and tool results as part of the agent workflow, which are untrusted third‑party outputs that could carry indirect prompt injection.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill explicitly configures runtime MCP endpoints (e.g. https://your-server.fastmcp.app/mcp and variants like https://catsmcp.fastmcp.app/mcp) in mcp_servers which are contacted during query execution to fetch tool definitions and invoke remote MCP tools that directly affect agent prompts/behavior, so this is a required runtime external dependency.
Audit Metadata