academic-research-companion
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill manages project state by reading and writing markdown files within the agent's local workspace (e.g., research/tracker.md). This activity is limited to research metadata and does not involve unauthorized access to sensitive system credentials or private user data.\n- [EXTERNAL_DOWNLOADS]: The skill utilizes web search and fetch tools to verify academic citations from established and well-known scholarly services including Google Scholar, arXiv, Semantic Scholar, and Zenodo. These network operations are fundamental to the skill's purpose of ensuring citation accuracy and preventing the generation of fabricated academic references.\n- [SAFE]: The skill instructions include clear guidance on data sensitivity, warning the user to avoid using non-public or sensitive professional data in public research artifacts unless it is authorized or abstracted. It also provides guidance on ethical research practices and coordination with institutional review boards (IRB).
Audit Metadata