smart-search
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a legitimate workflow for personal document search and summarization. It relies on the presence of a 'yuque-mcp' server and follows standard Retrieval-Augmented Generation (RAG) practices.
- [DATA_EXPOSURE]: The skill is designed to access personal information stored in Yuque knowledge bases. This access is conducted via explicit search and get tools within the user's session. No patterns suggestive of unauthorized data harvesting or exfiltration to external domains were found.
- [PROMPT_INJECTION]: The instructions focus on query extraction and document processing. There are no attempts to bypass model safety filters, ignore system instructions, or extract system prompts.
- [COMMAND_EXECUTION]: The skill does not request or use tools capable of executing shell commands, modifying system files, or performing network operations outside of the provided MCP tools.
Audit Metadata