skills/gitbyeos/open-part-skills/juya/Gen Agent Trust Hub

juya

Pass

Audited by Gen Agent Trust Hub on Jul 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The scripts rss-to-html.py and wx-to-html.py use the subprocess.run function to open the generated HTML reports in the user's default web browser using system-native commands like open or xdg-open.
  • [COMMAND_EXECUTION]: The script wx-to-html.py executes a local shell script (bin/wfp.sh) from the webfetch-plus dependency to perform web scraping of WeChat articles.
  • [EXTERNAL_DOWNLOADS]: The skill fetches data from specific external domains: daily.juya.uk for RSS feeds and mp.weixin.qq.com for news article content.
  • [PROMPT_INJECTION]: As the skill ingests content from external web pages, it is theoretically susceptible to indirect prompt injection or cross-site scripting (XSS). To mitigate this, the skill implements a robust WechatHTMLCleaner in scripts/juya_utils.py that uses a whitelist-based HTML parser to strip out unsafe tags and attributes before rendering the content.
  • [COMMAND_EXECUTION]: The skill uses importlib.util to dynamically load and execute its own helper script rss-to-html.py from a fixed relative path within the skill's own directory.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 29, 2026, 05:37 AM
Security Audit — agent-trust-hub — juya