The Agent Skills Directory

[PROMPT_INJECTION]: No malicious instruction overrides or safety bypass attempts were detected. The use of 'hats' as perspectives is a structured thinking technique and does not constitute a role-play jailbreak.
[DATA_EXFILTRATION]: No network commands or sensitive file access patterns were identified. The skill operates entirely within the provided context.
[REMOTE_CODE_EXECUTION]: The skill contains no executable scripts, dependency installations, or remote content fetching.
[COMMAND_EXECUTION]: No shell commands or system-level operations are present in the instructions or references.
[EXTERNAL_DOWNLOADS]: No external URLs or remote resources are referenced for download or execution.
[NO_CODE]: The skill is composed entirely of markdown documentation and logic instructions for the model, posing no risk of malicious code execution.

six-hats