skills/https-deeplearning-ai/sc-agent-skills-files/generating-practice-questions/Gen Agent Trust Hub
generating-practice-questions
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- PROMPT_INJECTION (LOW): The skill is vulnerable to Indirect Prompt Injection (Category 8) because it processes untrusted external data to generate output and code. * Ingestion points: Processes LaTeX, PDF (via pdfplumber), and Markdown files provided by users. * Boundary markers: The instructions do not define delimiters or specific 'ignore instructions' guards for the content extracted from lecture notes. * Capability inventory: The skill is instructed to generate functional Python code using powerful data science libraries (pandas, numpy, scikit-learn). * Sanitization: No sanitization or validation of input content is specified before it is interpolated into the generation prompt.
Audit Metadata