xiaohongshu-dashboard

Pass

Audited by Gen Agent Trust Hub on Feb 20, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • EXTERNAL_DOWNLOADS (LOW): The skill requires the installation of pandas and openpyxl via pip. While these are standard and reputable libraries, they are external dependencies installed at runtime.
  • COMMAND_EXECUTION (LOW): The skill workflow involves executing a local Python script (scripts/process_excel.py) to handle data processing. This is a standard operation for this type of tool.
  • INDIRECT_PROMPT_INJECTION / XSS (LOW): The skill ingests untrusted data from user-provided Excel files and embeds it into an HTML template.
  • Ingestion points: scripts/process_excel.py reads data from a user-specified .xlsx file.
  • Boundary markers: None are applied to the data within the Excel file.
  • Capability inventory: The skill executes a Python script, writes an index.html file to the local filesystem, and opens it in the default web browser.
  • Sanitization: The Python script does not perform HTML escaping on the content extracted from the Excel file (e.g., titles). If the resulting JSON is injected into a <script> tag in the HTML template without proper escaping, it could lead to Cross-Site Scripting (XSS) when the user views the dashboard.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 20, 2026, 01:40 AM