wechat-article-search

Pass

Audited by Gen Agent Trust Hub on Jul 23, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill makes network requests to weixin.sogou.com and v.sogou.com to fetch article search results and session cookies. These are well-known services associated with the skill's stated purpose.
  • [COMMAND_EXECUTION]: The skill uses local file system operations (fs.writeFileSync) specifically to save search results to a user-defined output path when requested via command-line arguments. This behavior is documented and functional.
  • [REMOTE_CODE_EXECUTION]: No remote code execution patterns were found. The skill depends on the standard cheerio package for HTML parsing.
  • [DATA_EXFILTRATION]: No sensitive local files (such as SSH keys, cloud credentials, or environment files) are accessed. Network activity is limited to the functionality of searching and resolving article URLs.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external HTML data from search results. While this represents a standard attack surface for any web-scraping tool, the script only extracts structured text fields (title, summary, date) into a JSON object, minimizing risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 23, 2026, 05:12 AM
Security Audit — agent-trust-hub — wechat-article-search