tutorial-writing
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill creates a surface where malicious instructions in codebase comments could influence the generated tutorial. Ingestion points: Step 2 (Deep Codebase Research) reads project files. Boundary markers: Absent; no delimiters are defined to isolate codebase content. Capability inventory: File reading and writing (Markdown); no execution or network capabilities. Sanitization: Absent; content is used directly to form the tutorial.
Audit Metadata