deep-research
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses established Model Context Protocol (MCP) tools (firecrawl and exa) for web searching and scraping. These are standard tools for information retrieval and do not represent unauthorized data access.
- [SAFE]: The workflow emphasizes citation, source attribution, and cross-referencing, which are defensive measures against misinformation and hallucination.
- [SAFE]: The 'Parallel Research with Subagents' section describes using standard agent orchestration to handle complex tasks, which is a common and safe practice in modern AI agent workflows.
- [SAFE]: No obfuscation, prompt injection, or persistence mechanisms were found. The skill operates within the expected boundaries of a research-oriented tool.
Audit Metadata