The Agent Skills Directory

[SAFE]: The skill consists entirely of Markdown instructions, templates, and guidelines for writing articles and answers. No malicious patterns were detected.
[NO_CODE]: This skill does not include any executable scripts (Python, Node.js, or Shell). It operates purely through natural language instructions for the AI agent.
[INDIRECT_PROMPT_INJECTION]: The skill allows for processing user-provided text (e.g., 'Optimize Answer' feature). While this creates an ingestion point for potentially untrusted data, the skill possesses no dangerous capabilities such as file system access, network requests, or subprocess execution, rendering the risk negligible.

zhihu-writer