fastmcp-server
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches documentation and API references from the official FastMCP documentation site (gofastmcp.com).- [INDIRECT_PROMPT_INJECTION]: The skill processes external documentation which represents a potential attack surface for indirect prompt injection.
- Ingestion points: Documentation index (llms.txt) and markdown pages from gofastmcp.com as specified in SKILL.md.
- Boundary markers: No specific boundary markers or 'ignore' instructions are mentioned for the external content.
- Capability inventory: The skill guides the agent in authoring MCP tools, resources, and prompts, and testing them using the FastMCP Client.
- Sanitization: No specific sanitization or validation of the documentation content is performed.- [SAFE]: The skill provides defensive programming advice, specifically cautioning against leaking sensitive backend details in error messages by masking ordinary exceptions like ValueError while using explicit error types for client-facing messages.
Audit Metadata