The Agent Skills Directory

[SAFE]: The skill consists exclusively of Markdown documentation and YAML configuration. It contains no executable scripts, shell commands, or binary files.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process user input through collaborative interviews and requirements shaping. While this creates a natural surface for indirect prompt injection, the risk is negligible because the skill does not utilize high-privilege tools such as network access, arbitrary shell execution, or sensitive credential access. The instructions explicitly direct the agent to honor existing authorizations.
[DATA_EXPOSURE]: There are no patterns involving the access or exfiltration of sensitive files, environment variables, or hardcoded credentials. The only file operation mentioned is the creation of a 'brief' document in a standard project directory.
[REMOTE_CODE_EXECUTION]: No remote code execution patterns, external package installations, or dynamic code evaluation techniques were identified.

shape-requirements