Skills
skills/moeru-ai/airi/minecraft-debug-mcp/Gen Agent Trust Hub

minecraft-debug-mcp

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The execute_repl tool enables the execution of arbitrary code within the Minecraft bot's internal environment (references/mcp-surface.md).
  • [COMMAND_EXECUTION]: The skill instructions direct the agent to execute the pnpm dev command locally to initialize the bot service (SKILL.md).
  • [PROMPT_INJECTION]: The skill exposes an indirect prompt injection surface through tools that accept external simulated input (references/mcp-surface.md).
  • Ingestion points: The inject_chat and inject_event tools in references/mcp-surface.md.
  • Boundary markers: Absent. No specific delimiters or safety instructions isolate injected content.
  • Capability inventory: The bot possesses the execute_repl tool (references/mcp-surface.md) which allows arbitrary code execution.
  • Sanitization: Absent. The skill does not define any sanitization or validation for content provided to the injection tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 04:17 AM