zhihu-post

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Python script (scripts/zhihu_prepare.py) to convert Markdown to HTML and perform word count validation.
  • [COMMAND_EXECUTION]: The skill utilizes browser actions to execute JavaScript in the user's Chrome session to automate the Zhihu post editor. This is restricted to the user's local environment.
  • [PROMPT_INJECTION]: The skill processes user-supplied post titles and content. Ingestion points: User inputs for title and content. Boundary markers: None present. Capability inventory: Local script execution and browser automation (tab access, snapshot, and click/type actions). Sanitization: The Python script provides basic Markdown formatting but does not include advanced sanitization of HTML attributes like href, though it primarily uses insertText for browser interaction.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 11:41 AM