deep-research
Pass
Audited by Gen Agent Trust Hub on Apr 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a logical and secure workflow for automated research. It utilizes specific tools like firecrawl and exa for web search and scraping, which is consistent with its stated purpose.- [COMMAND_EXECUTION]: The instructions involve the use of MCP tools for web interaction. These operations are scoped to research queries and URL content retrieval, following established patterns for search agents.- [DATA_EXFILTRATION]: No unauthorized data transfer or credential harvesting patterns were detected. The skill's network operations are restricted to searching and fetching content for the user's research report.
Audit Metadata