The Agent Skills Directory

[SAFE]: The skill utilizes legitimate Model Context Protocol (MCP) tools (alphaxiv and semantic-scholar) to search for public academic papers. These are recognized tools for academic research and do not represent a security risk.
[SAFE]: No hardcoded credentials or sensitive file paths were detected. The mention of SS_API_KEY refers to standard environment variable configuration for rate limiting with the Semantic Scholar API, which is a secure practice.
[SAFE]: The skill includes a <HARD-GATE> section that explicitly instructs the agent to limit its output to orientation only and prohibits drawing substantive conclusions from abstracts. This acts as a logical boundary to prevent the agent from being misled by content within external data.
[SAFE]: No obfuscation, dynamic code execution, or persistence mechanisms were found. The workflow is entirely focused on data retrieval and structured presentation.

Literature Overview