wren-generate-mdl
Pass
Audited by Gen Agent Trust Hub on May 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill performs a version check by retrieving a JSON file from the vendor's official GitHub repository (Canner/wren-engine).
- [COMMAND_EXECUTION]: The workflow relies on the 'wren' CLI and various database connection libraries (e.g., SQLAlchemy, psycopg) to perform schema discovery, project initialization, and validation.
- [PROMPT_INJECTION]: There is an inherent surface for indirect prompt injection because the skill ingests metadata (table and column names) directly from a database.
- Ingestion points: Phase 2 (Database schema introspection).
- Boundary markers: Not present in the instructions.
- Capability inventory: Local file system writes and CLI command execution.
- Sanitization: No specific sanitization or escaping of database metadata is described prior to generating YAML configuration files.
Audit Metadata