moai-workflow-project
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE] (SAFE): No malicious behaviors or security risks detected.
- The provided files are purely declarative, containing documentation, JSON schemas for configuration validation, and markdown templates for project documentation.
- No executable scripts (Python/Node.js/Shell) were provided in the analyzed file set; logic appears to reside in referenced but missing modules.
- Sensitive field definitions (e.g.,
api_keyinlanguage_config) are correctly handled as schema definitions and placeholders rather than hardcoded secrets. - [INDIRECT_PROMPT_INJECTION] (LOW): The skill implements a template-based documentation system (e.g.,
tech-template.md,product-template.md). - Ingestion points: Data enters the system via project configuration files that are interpolated into templates using double-curly brace syntax (e.g.,
{{ENFORCEMENT_TOOLS}}). - Boundary markers: None identified in the provided templates; there are no explicit instructions for the AI to ignore embedded content during interpolation.
- Capability inventory: The schema defines capabilities for package management (
pip,npm), git initialization, and documentation generation, though the execution logic is not provided. - Sanitization: There is no evidence of sanitization or escaping of the user-provided configuration data before it is inserted into markdown blocks, which could potentially lead to the agent interpreting data as instructions if it processes the rendered documentation.
Audit Metadata