The Agent Skills Directory

[SAFE]: The skill provides structured guidance and templates for project management without including any executable scripts, network operations, or hardcoded credentials. All external references point to internal documentation files within the skill's own repository structure.
[INDIRECT_PROMPT_INJECTION]: The skill architecture handles external data (project specifications and user feedback) which represents a theoretical surface for indirect prompt injection. However, the NEXUS operating model described in the skill includes robust defensive measures, specifically the 'Reality Checker' and 'Evidence Collector' quality gates, which require documented proof of implementation and compliance before proceeding, significantly mitigating the risk of accidental or malicious instruction execution from processed data.

strategy