amazon-review-checker
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The
scripts/report_html.pyscript generates an HTML report by interpolating review content directly into HTML tags and JavaScript strings usinginnerHTMLwithout prior sanitization. - Evidence:
scripts/report_html.pycontainscontainer.innerHTML += ... ${review.content} ...and{summary}interpolated into<strong>tags. - Impact: If the skill processes reviews containing malicious HTML or JavaScript, those payloads will be active in the generated
review_analysis_report.html. A user opening this report in a browser would be vulnerable to Cross-Site Scripting (XSS). - [DYNAMIC_EXECUTION]: The skill uses local scripts to generate a new file on the file system based on analyzed data.
- Evidence:
scripts/report_html.pyuseswith open(output_path, 'w', encoding='utf-8') as f: f.write(html)to write the generated report to disk. - [EXTERNAL_DOWNLOADS]: The generated HTML report fetches external resources for data visualization.
- Evidence: The report template in
scripts/report_html.pyincludes<script src="https://cdn.jsdelivr.net/npm/chart.js"></script>. - Note: This reference targets a well-known and trusted CDN service for the Chart.js library.
Audit Metadata