wechat-article-fetcher

Pass

Audited by Gen Agent Trust Hub on Mar 8, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the download of Chromium browser binaries using the Playwright framework, an official tool provided by Microsoft.\n- [COMMAND_EXECUTION]: Installation requires running the playwright install chromium command, which executes a setup script to install the necessary browser environment.\n- [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection (Category 8) due to its data-fetching capabilities.\n
  • Ingestion points: Untrusted content is ingested from external WeChat URLs in wechat_fetcher.py.\n
  • Boundary markers: The skill does not implement delimiters or 'ignore' instructions to isolate fetched content from agent instructions.\n
  • Capability inventory: The script allows writing the fetched content to local files through the output_path argument.\n
  • Sanitization: The extracted text is not sanitized or filtered, meaning any malicious instructions within an article could be passed directly to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 8, 2026, 02:24 AM