writing-crypto
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE] (SAFE): The skill consists entirely of Markdown instructions and LaTeX examples. It contains no scripts (Python, Node.js, Shell) or executable components, eliminating risks associated with command execution or remote code execution.
- [DATA_EXPOSURE] (SAFE): The skill mentions local file paths (/home/dbosk/phd/thesis/). While this reveals a specific directory structure and username, it does not reference sensitive system files or credentials.
- [PROMPT_INJECTION] (SAFE): No instructions designed to override AI safety filters or bypass system prompts were detected.
Audit Metadata