academic-research
Pass
Audited by Gen Agent Trust Hub on Aug 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill describes legitimate academic search functionality across repositories such as arXiv, PubMed, and Semantic Scholar. No data exfiltration or credential harvesting patterns were observed.
- [SAFE]: Mentions of local paths, such as
/Users/alice/worlds/l/mcp_servers.json, are provided as illustrative examples for user configuration of Model Context Protocol (MCP) servers and do not involve automated unauthorized access. - [SAFE]: Documentation regarding external server installation via
npxserves as a template for user-initiated extensions rather than automated or hidden code execution by the agent.
Audit Metadata