skills/bighardperson/computer-science-skills-collection/playwright-scraper-skill/Gen Agent Trust Hub
playwright-scraper-skill
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, prompt injections, or obfuscation techniques were detected across the skill's scripts and documentation.
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the 'playwright' package and its associated Chromium browser via standard NPM commands (
npm install,npx playwright install). These are necessary for the skill's documented functionality. - [COMMAND_EXECUTION]: The skill uses Node.js and Bash scripts to automate browser interactions. All command executions (e.g., launching Chromium via Playwright) are standard for the intended scraping purpose.
- [DATA_EXFILTRATION]: No unauthorized network operations or data exfiltration patterns were found. The skill only communicates with the URLs explicitly provided for scraping and saves results (HTML, screenshots) to local paths defined by the user.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the web (via
page.evaluateandinnerText). While it does not implement specific sanitization before returning content to the agent, this is typical for scraper tools. The risk is considered minimal and within the expected operational scope.
Audit Metadata