The Agent Skills Directory

[SAFE]: The skill follows security best practices and does not include any suspicious remote code execution, external downloads, or data exfiltration patterns. All operations are performed locally via the 'trekker' CLI.
[COMMAND_EXECUTION]: The skill executes 'trekker' CLI commands (e.g., trekker task list, trekker comment add) to manage project state. This behavior is transparently documented and aligned with the skill's primary purpose.
[PROMPT_INJECTION]: While the agent reads content from task descriptions and comments which could theoretically host indirect injection attempts, this is a standard risk for task management tools and is handled by the model's internal safety guidelines.

trekker