The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown instructions for persona adoption and business role-playing. It does not include any executable code, shell scripts, or tool-use definitions.
[PROMPT_INJECTION]: The instructions focus on defining a character and logic framework for business advice. No attempts to bypass safety filters, extract system prompts, or override agent constraints were detected.
[DATA_EXFILTRATION]: The skill does not include any commands for accessing sensitive files or performing network requests. No hardcoded credentials or API keys are present.
[REMOTE_CODE_EXECUTION]: There are no remote script downloads or dynamic code execution patterns. The skill does not define any external dependencies or package requirements.
[OBFUSCATION]: No hidden text, encoded strings, or malicious Unicode characters were found in any of the analyzed files.

liuyonghao-perspective