The Agent Skills Directory

[SAFE]: The skill operates locally on markdown files within a specific directory structure. It does not perform any network operations or external data transmissions.
[SAFE]: All included scripts (task_manager.py, next_number.py) use only standard Python libraries and do not utilize dangerous functions such as eval(), exec(), or subprocess calls.
[SAFE]: The 'Kanban Sovereignty' rules are functional instructions designed to maintain the integrity of sequential task IDs and do not attempt to bypass agent safety filters.
[SAFE]: No hardcoded credentials or sensitive file paths (outside of the project's own task directories) were detected.
[SAFE]: While the skill reads task content, the lack of network access or dangerous system capabilities mitigates the risk of indirect prompt injection to a safe level.

task-agent