The Agent Skills Directory

Category 1: Prompt Injection (SAFE): The skill's instructions focus exclusively on educational pedagogy and formatting requirements. There are no attempts to override safety filters or bypass system instructions.\n- Category 2: Data Exposure & Exfiltration (SAFE): No hardcoded secrets, sensitive file paths, or network operations were detected. The skill interacts only with local quiz files and the provided formatting script.\n- Category 4: Unverifiable Dependencies & Remote Code Execution (SAFE): The included script (redistribute_answers.py) is self-contained and utilizes only Python standard libraries (re, sys, pathlib). It does not download external content or execute remote code.\n- Category 8: Indirect Prompt Injection (SAFE): While the skill ingests user-defined or AI-generated quiz content, it processes this data through a static parsing script for reformatting rather than executing it. The capability surface is restricted to local file manipulation for the primary task.\n- Category 10: Dynamic Execution (SAFE): The Python script performs safe string manipulation to reorder quiz options. It avoids dangerous functions like eval() or exec(), ensuring that question content is handled strictly as data.

quiz-generator