The Agent Skills Directory

[SAFE]: The skill functions as a set of instructions for the AI to transform user objectives into a markdown roadmap. It includes a template file used for formatting the output.
[PROMPT_INJECTION]: Analysis of the skill instructions and metadata revealed no attempts to bypass safety filters or override system behavior.
[DATA_EXFILTRATION]: No network tools (like curl or wget) or access to sensitive local files (like .env or .ssh) were found. The skill only defines paths for saving the generated documentation.
[COMMAND_EXECUTION]: The skill does not use any tool invocations or shell commands. The use of $ARGUMENTS is a placeholder for user-provided input and does not facilitate command injection in this context.
[REMOTE_CODE_EXECUTION]: There are no patterns indicating the download or execution of remote scripts or unverified dependencies.

agile-roadmap