The Agent Skills Directory

[SAFE]: The skill operates as a design system utility. It reads structured configuration from a local styles/ directory and writes documentation to a project's branding folder. No network access or remote execution patterns were detected.
[COMMAND_EXECUTION]: The skill instructions include running a local utility script node bin/theme-css.js. The input to this command is validated against a pre-defined set of local YAML files, which prevents arbitrary command injection or malicious argument passing.
[PROMPT_INJECTION]: A thorough review of all 79 files, including design philosophies and CSS guidelines, revealed no attempts to override agent behavior, bypass safety filters, or extract system prompts.
[DATA_EXFILTRATION]: The skill does not access sensitive user directories (such as .ssh or .aws) and lacks tools or instructions to transmit data to external servers. All operations are confined to the defined design and project directories.

gsp-style