The Agent Skills Directory

[SAFE]: The skill performs legitimate text processing tasks. The included Python script (scripts/rewrite.py) was audited and found to contain only safe operations using Python's standard library to read a local configuration file. It does not initiate network connections, access sensitive user directories, or use dangerous functions like eval() or subprocess.
[SAFE]: No hardcoded credentials, API keys, or sensitive file paths were found. The skill documentation explicitly states a 'zero-dependency' and 'no network' design, which is verified by the source code.
[SAFE]: No prompt injection or behavior override patterns were detected in the instructions. The rules in assets/platform-rules.md are standard formatting and stylistic guidelines for the AI agent.
[SAFE]: No obfuscation techniques, hidden characters, or suspicious encoding were found in any of the skill files.

zhihu-rewrite