The Agent Skills Directory

[SAFE]: The skill functions as a quality assurance checklist for software design and implementation, focusing on best practices like WCAG compliance and design system adherence.
[PROMPT_INJECTION]: No attempts to bypass safety filters, extract system prompts, or override agent behavior were detected. The use of instructional markers such as 'IMPORTANT' and 'CRITICAL' is limited to workflow prioritization.
[DATA_EXFILTRATION]: The skill does not contain instructions to access sensitive files (e.g., credentials, SSH keys) or transmit data to external servers.
[REMOTE_CODE_EXECUTION]: No patterns involving the download of external scripts, package installations from untrusted sources, or dynamic execution of remote code were found.
[COMMAND_EXECUTION]: The skill refers to an internal command /impeccable for preparation, which is a standard pattern for sub-skill invocation and does not involve risky shell command execution.

polish