The Agent Skills Directory

[SAFE]: The skill follows security best practices for its intended purpose. It facilitates the creation of project documentation by gathering user input and saving it to a structured markdown file within the project's workspace.
[PROMPT_INJECTION]: The skill utilizes the $ARGUMENTS variable to ingest initial context. While it does not implement explicit boundary markers or sanitization for this untrusted input (a surface for indirect prompt injection), the risk is minimal because the agent is instructed to only generate documentation artifacts and avoid implementation, and no dangerous tools or network operations are involved.
[COMMAND_EXECUTION]: The skill includes logic to save files to planning/<initiative>/intake.md. This is a localized file system operation restricted to the project's directory and does not involve privilege escalation, access to sensitive system files, or arbitrary command execution.

agile-intake