The Agent Skills Directory

[SAFE]: The skill implements a legitimate task management workflow for requirements gathering and task decomposition using standard tools.
[PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes untrusted user-supplied data into structured task lists and PRDs.
Ingestion points: User-provided feature descriptions in Phase 2 and acceptance criteria in Phase 5.
Boundary markers: Absent; the output templates do not use explicit delimiters or instructions to ignore embedded commands in the user's input.
Capability inventory: The skill utilizes Read, Write, Glob, and Grep tools to manage plan files and action reports.
Sanitization: No explicit sanitization or validation of user-provided text is defined before interpolation into output files.

create-task-batch