Skills
skills/mjunaidca/mjs-agent-skills/building-mcp-servers/Gen Agent Trust Hub

building-mcp-servers

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION] (SAFE): The file scripts/connections.py implements MCPConnectionStdio, which utilizes the stdio_client from the mcp library to spawn subprocesses. This is the standard and necessary method for a client to communicate with a local MCP server.
  • [EXTERNAL_DOWNLOADS] (SAFE): SKILL.md instructs the agent to fetch documentation and SDK READMEs from official sources such as modelcontextprotocol.io and raw.githubusercontent.com/modelcontextprotocol. These are legitimate resources required for the skill's educational purpose.
  • [INDIRECT_PROMPT_INJECTION] (LOW): The skill is designed to ingest and process external documentation which could theoretically contain malicious instructions.
  • Ingestion points: External protocol and API documentation URLs listed in SKILL.md Phase 1.2 and 1.3.
  • Boundary markers: Absent; the instructions do not specify delimiters for the fetched content.
  • Capability inventory: scripts/connections.py provides the ability to execute local commands (via stdio transport).
  • Sanitization: None detected in the documentation processing phase.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:39 PM