Skills
skills/vanman2024/ai-dev-marketplace/fastmcp-integration/Gen Agent Trust Hub

fastmcp-integration

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • SAFE (SAFE): The skill contains legitimate boilerplate code and documentation for FastMCP integration.\n- Indirect Prompt Injection (SAFE): The provided examples use the query function to process user prompts, which is a standard capability of the SDK. No malicious patterns were found targeting this surface.\n
  • Ingestion points: prompt argument in query() found in connection-status.py and fastmcp-cloud-http.py.\n
  • Boundary markers: Absent in minimal examples.\n
  • Capability inventory: Tool execution is scoped to specified MCP servers via allowed_tools.\n
  • Sanitization: Absent in examples, following standard SDK usage patterns.\n- Privilege Escalation (SAFE): The inclusion of permission_mode="bypassPermissions" in fastmcp-cloud-http.py is explicitly documented as being for demonstration purposes and represents a standard configuration option for the SDK in testing environments.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:28 PM