The Agent Skills Directory

[SAFE]: The skill is a standard usability engineering tool designed for analytical evaluation of user interfaces. It follows established UX methodologies.
[COMMAND_EXECUTION]: No dangerous command execution patterns were found. The skill utilizes Mermaid diagrams for visualization, which is an expected and safe feature for reporting and documentation.
[DATA_EXFILTRATION]: There are no indicators of data exfiltration. The skill does not perform network requests and focuses on generating internal documentation based on provided UI descriptions.
[PROMPT_INJECTION]: The instructions are focused on guiding the agent through a specific analytical process. There are no attempts to bypass safety filters or override core agent behavior.
[CREDENTIALS_UNSAFE]: No hardcoded credentials, API keys, or sensitive environment variable accesses were detected.

cognitive-walkthrough