wechat-article-search
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill's primary functionality is invoked via shell commands (e.g.,
node scripts/search_wechat.js "关键词"). This creates a surface for command injection if the agent or platform does not adequately sanitize user-provided keywords before passing them to the shell execution environment. - [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
cheeriolibrary from the NPM registry. This is a standard dependency for the skill's HTML parsing logic and is documented in the setup instructions. - [INDIRECT_PROMPT_INJECTION]: The skill fetches and parses external content from search results and article summaries. Since this untrusted data is returned to the agent's context, there is a possibility that malicious content embedded in the search results could attempt to influence the agent's behavior.
- Ingestion points: Network requests to
weixin.sogou.cominscripts/search_wechat.js. - Boundary markers: None identified in the output provided to the agent.
- Capability inventory: File system writing (
fs.writeFileSync) and network operations viahttpsmodule. - Sanitization: The script extracts text from HTML elements but does not explicitly filter for prompt injection patterns or Markdown control characters.
Audit Metadata