moai-project-config-manager

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed for local project configuration management within the .moai/ directory. It uses standard file operations to perform CRUD tasks on a JSON configuration file.
  • [COMMAND_EXECUTION]: The skill includes a local validation script (validate.py) and utilizes standard system tools for file manipulation, which are consistent with its documented purpose.
  • [PROMPT_INJECTION]: The instructions and examples focus strictly on configuration logic and state management. There are no attempts to override agent safety protocols or hijack the conversation flow.
  • [DATA_EXFILTRATION]: The skill does not perform any network operations. Data access is restricted to the project-specific configuration files, and no access to sensitive system paths or credentials was found.
  • [INDIRECT_PROMPT_INJECTION]: While the skill processes user-controlled data (project settings), it implements strong sanitization.
  • Ingestion points: .moai/config/config.json.
  • Boundary markers: Uses a strict JSON schema for structural validation.
  • Capability inventory: File writing and local command execution (for validation).
  • Sanitization: Implements character limits (e.g., 20 chars for nickname) and regex-based input validation (^[a-zA-Z0-9가-힣ぁ-ゔ一-龯\s]+$) to prevent malicious payload injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 01:06 AM