universal-writer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE] (SAFE): A comprehensive review of the 12 files reveals no malicious behavior. The skill performs localized file operations and string interpolation using the Jinja2 library. No instances of obfuscation, credential harvesting, or unauthorized network calls were detected.\n- [Indirect Prompt Injection] (SAFE): The skill processes external JSON and CSV data through 'data_parser.py' to populate Markdown templates. While this creates a data ingestion surface, it is the primary intended function of the writing tool. The logic uses standard parsing and templating techniques without any observed bypass or injection vulnerabilities.
Audit Metadata