wechat-article-fetcher

Pass

Audited by Gen Agent Trust Hub on Mar 21, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The script downloads article content and image resources from official WeChat domains (mp.weixin.qq.com) and associated content delivery networks. This is the primary function of the skill and uses standard HTTP GET requests via the axios library.
  • [PROMPT_INJECTION]: The skill processes untrusted third-party content from the web, creating a potential surface for indirect prompt injection. If a fetched article contains instructions designed to manipulate an AI agent, those instructions will be included in the generated Markdown output.
  • Ingestion points: The scripts/fetch.js file fetches arbitrary HTML content from user-provided WeChat URLs.
  • Boundary markers: The skill does not implement specific delimiters or 'ignore' instructions in the generated output to isolate the untrusted content from the rest of the agent's context.
  • Capability inventory: The skill has file system write access (fs.writeFileSync) and network read access (axios.get).
  • Sanitization: The script performs basic sanitization of filenames to ensure compatibility and escapes colons in metadata to maintain YAML structure.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 21, 2026, 10:11 AM