The Agent Skills Directory

[PROMPT_INJECTION]: The skill provides detailed instructions on persona adoption and writing style. These instructions are standard for defining AI behavior and do not attempt to bypass safety filters or override system constraints in a malicious way. The 'Prohibited List' is used to improve writing quality rather than restrict safety protocols.- [DATA_EXFILTRATION]: No sensitive file paths, environment variables, or hardcoded credentials were found. References to external websites such as 'jackyshen.com' are provided as context and documentation, not as exfiltration targets.- [REMOTE_CODE_EXECUTION]: There are no commands or scripts that fetch or execute remote code. The content is entirely instructional text.- [COMMAND_EXECUTION]: No shell commands, subprocess calls, or system-level operations are included in the skill.- [OBFUSCATION]: The content is written in clear, plain text (Markdown/Chinese/English). No Base64, hex encoding, or hidden characters were detected.- [PRIVILEGE_ESCALATION]: The skill does not request or attempt to gain elevated permissions or modify system configurations.- [PERSISTENCE]: No mechanisms for maintaining long-term access or scheduled tasks are present.- [INDIRECT_PROMPT_INJECTION]: While the skill is designed to process user input for rewriting, it does not possess autonomous network or file-writing capabilities that would create a high-risk attack surface.

my-writing-style