The Agent Skills Directory

[SAFE]: No security issues were detected during the analysis of the skill. The instructions and metadata were evaluated for all threat categories including injection, exfiltration, and obfuscation, and were found to be benign.
[NO_CODE]: The skill consists entirely of markdown-based templates, checklists, and analytical frameworks intended for human or AI-guided manual review. It does not contain any executable scripts, shell commands, or automated data processing capabilities that could be exploited.

ma-due-diligence