zhihu-hot-scraper
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes
browser_run_code_unsafeto execute JavaScript snippets within the browser context for scraping hot topics and answers. These scripts are provided in plain text and perform standard DOM traversal. - [EXTERNAL_DOWNLOADS]: It references the official Playwright MCP (
@playwright/mcp) from the NPM registry as a requirement for execution. NPM is a well-known and trusted service for package management. - [PROMPT_INJECTION]: The skill involves ingesting data from the Zhihu website. It includes logic to clean the data (specifically removing zero-width characters like U+200B) and isolates the scraped content within generated Markdown files to prevent indirect influence on the agent's behavior.
Audit Metadata