The Agent Skills Directory

[SAFE]: The skill implements a project management workflow for creating 'tracks' (features, bugs, etc.). It reads and writes to a local conductor/ directory to maintain project context.
[SAFE]: No external network requests, remote code execution, or suspicious command patterns were detected. All file operations are scoped to the project environment.
[INDIRECT_PROMPT_INJECTION]: While the skill ingests user input for summaries and user stories, it does so through an interactive Q&A process. The risk of indirect injection is low as the data is used to generate documentation rather than being executed as code.
[DYNAMIC_EXECUTION]: The skill uses placeholders for track IDs and metadata, but these are simple string substitutions within markdown and JSON templates, posing no dynamic execution risk.

conductor-new-track