The Agent Skills Directory

[SAFE]: The skill performs legitimate workspace setup and profile generation tasks as described in its purpose.
[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by processing conversational user input to populate configuration files.
Ingestion points: Natural language user responses regarding name, role, interests, and projects are captured during the onboarding flow in SKILL.md.
Boundary markers: Absent. User input is directly interpolated into markdown templates without specific delimiters or warnings to ignore embedded instructions.
Capability inventory: The skill uses file and directory creation capabilities to write markdown files across the 00-inbox/, 03-professional/, and 04-projects/ directories.
Sanitization: The skill does not implement explicit validation or escaping for user-provided strings before writing them to the file system.

onboarding