The Agent Skills Directory

[SAFE]: The skill's primary function is to interact with the Zhihu editor through a browser extension. All operations are performed within the context of the user's existing login session, and no sensitive information is exfiltrated to external servers.
[COMMAND_EXECUTION]: The skill executes a local Python script (scripts/zhihu_prepare.py) to process Markdown content. The script uses standard regex for text conversion and does not involve any dangerous functions such as eval(), exec(), or untrusted system calls.
[DATA_EXFILTRATION]: No unauthorized network activity or data exfiltration patterns were detected. All network communication is handled via the Browser Relay extension to the official Zhihu domain.
[PROMPT_INJECTION]: The skill instructions in SKILL.md are purely functional and do not contain patterns intended to bypass AI safety filters or override system instructions.

zhihu-post