wechat-article-search
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to run a local Node.js script (
scripts/search_wechat.js) to perform web scraping and data processing tasks. This execution is an intended part of the skill's functionality. - [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it ingests and processes untrusted article metadata (titles and summaries) from the web.
- Ingestion points: Article data is fetched from external search results via HTTPS requests in
scripts/search_wechat.js. - Boundary markers: Absent. Results are returned to the agent without specific delimiters or instructions to ignore potential commands embedded in the search results.
- Capability inventory: The skill uses
BashandReadpermissions to execute its scripts and handle data. - Sanitization: No specific sanitization or filtering of the fetched text is performed before it is passed to the agent context.
Audit Metadata