grilling-page
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The test suite (scripts/test_check_question_page.py) uses subprocess.run() to execute the local validation script (scripts/check_question_page.py) using the current Python interpreter. This execution is limited to internal testing and does not process untrusted external commands.\n- [EXTERNAL_DOWNLOADS]: The skill's HTML template (assets/question-page.html) references stylesheets and fonts from Google's official domains (fonts.googleapis.com and fonts.gstatic.com). These are well-known and trusted services used for interface styling.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external project sources (files, tickets, PRs) to generate its questions. It mitigates potential injection risks through a dedicated validator script (scripts/check_question_page.py) that implements a whitelist-based HTML sanitizer, ensuring that only safe, specific tags and HTTPS-only links are included in the generated output.
Audit Metadata