wechat-article-search
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill connects to weixin.sogou.com and mp.weixin.qq.com to retrieve search results and article details, which are well-known domains consistent with the tool's purpose.
- [COMMAND_EXECUTION]: The scripts/search_wechat.js script is capable of writing search results to a local file using fs.writeFileSync when the user provides an output path.
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests untrusted external data.
- Ingestion points: Article titles and summaries are scraped from the web in scripts/search_wechat.js.
- Boundary markers: There are no explicit delimiters or instructions to prevent the agent from following commands embedded in the scraped article data.
- Capability inventory: The skill has file writing capabilities through the fs.writeFileSync function in scripts/search_wechat.js.
- Sanitization: The scraped article content is not sanitized or filtered for potential malicious prompt content.
Audit Metadata