The Agent Skills Directory

[SAFE]: No security issues or malicious patterns were detected. The skill operates entirely on local data provided within the skill package.
[COMMAND_EXECUTION]: The skill utilizes Bash commands including perl and shuf to randomly select lines from its internal seeds.md file. This command execution is scoped to the skill's own directory and is used purely for the functional purpose of providing random creative prompts.
[PROMPT_INJECTION]: While the skill intentionally uses 'cognitive disruptors' to influence the agent's internal reasoning process for creative tasks, these instructions are functional and do not attempt to bypass safety filters, extract system prompts, or override core safety guidelines.

creative-seeds