wechat-article-fetcher

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill fulfills its stated purpose of fetching and saving WeChat article content. No malicious behaviors such as data exfiltration to unauthorized domains or credential harvesting were found.
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the 'playwright' Python package and the Chromium browser. These are standard dependencies for the tool's browser automation functionality.
  • [COMMAND_EXECUTION]: The script uses Playwright's page.evaluate() to execute JavaScript within the browser context to extract text content from the article's DOM. This execution is limited to the browser environment and is a standard technique for web scraping.
  • [SAFE]: The tool processes content from external URLs, which introduces a potential surface for indirect prompt injection.
  • Ingestion points: wechat_fetcher.py (content fetched from WeChat URLs via Playwright)
  • Boundary markers: None identified
  • Capability inventory: File writing, network access (browser-based)
  • Sanitization: Content is extracted as plain text, but no specific instruction filtering is performed on the data
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 01:11 AM