researching-with-playwright

Pass

Audited by Gen Agent Trust Hub on Apr 4, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends installing Playwright via npm init playwright@latest, which downloads the automation framework and browser binaries from official sources.\n- [COMMAND_EXECUTION]: The provided Node.js scripts (basic-scraper.js, extract-documentation.js) execute browser automation tasks and write results to the local file system. These actions are consistent with the skill's purpose of web scraping and research.\n- [DATA_EXFILTRATION]: The skill performs network operations to access websites for research. No patterns were found indicating the exfiltration of sensitive local data to unauthorized external servers.\n- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes arbitrary web content.\n
  • Ingestion points: External web content is ingested via page.goto(url) in both scripts/basic-scraper.js and scripts/extract-documentation.js.\n
  • Boundary markers: No specific delimiters or safety instructions are used to wrap extracted content within the resulting files.\n
  • Capability inventory: The scripts have the ability to write files (fs.writeFile), capture screenshots, and generate PDFs based on the processed web data.\n
  • Sanitization: The documentation extractor implements basic text truncation, but does not perform comprehensive sanitization or validation of the ingested web content.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 4, 2026, 01:44 PM
Security Audit — agent-trust-hub — researching-with-playwright