weixin-reader-plus

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes external HTML content from WeChat URLs which may contain untrusted data.
  • Ingestion points: The script weixin_reader.py fetches article content via the read_wechat_article function.
  • Boundary markers: Output content is separated by text delimiters (--- 正文内容 ---) as defined in SKILL.md, but no explicit instructions are provided to the agent to ignore embedded commands.
  • Capability inventory: The skill's capabilities are limited to performing HTTP GET requests and printing extracted text to standard output.
  • Sanitization: The script uses BeautifulSoup's get_text method to remove HTML tags, but it does not perform semantic filtering or sanitization of the natural language content for potential instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 07:45 PM
Security Audit — agent-trust-hub — weixin-reader-plus