skills/cerico/macfair/mcp/Gen Agent Trust Hub

mcp

Pass

Audited by Gen Agent Trust Hub on Feb 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches the official Model Context Protocol (SDK) and the Zod validation library from the NPM registry. It also references documentation and example repositories from Anthropic's official GitHub account.- [COMMAND_EXECUTION]: Provides instructions to run shell commands for project initialization, package installation, and local server testing using pnpm and node.- [PROMPT_INJECTION]: The provided tool templates for database queries and API calls create an indirect prompt injection surface by processing user-supplied arguments.
  • Ingestion points: User input enters through the 'sql' argument in the query tool and the 'city' argument in the weather tool.
  • Boundary markers: No explicit delimiters or instruction-bypass warnings are present in the code snippets.
  • Capability inventory: The templates demonstrate capabilities for database interaction (pg), file system access (readdir), and external network requests (fetch).
  • Sanitization: The SQL template includes a basic validation check to restrict queries to SELECT statements, which reduces but does not eliminate injection risks.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 24, 2026, 12:30 PM