Skills
skills/szoloth/skills/playwright/Gen Agent Trust Hub

playwright

Pass

Audited by Gen Agent Trust Hub on May 5, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads the @playwright/mcp package from the npm registry, which is an official and trusted Microsoft dependency.
  • [COMMAND_EXECUTION]: Executes the Playwright CLI tool via a shell wrapper to perform browser automation tasks.
  • [REMOTE_CODE_EXECUTION]: Features eval and run-code capabilities that allow JavaScript execution within the browser, which is a core function for web automation.
  • [DATA_EXFILTRATION]: Accesses and extracts data from web pages via screenshots and snapshots as part of its documented workflow.
  • [SAFE]: The skill's behavior is consistent with its intended use as a browser automation tool, and all external dependencies are from trusted vendors.
  • [PROMPT_INJECTION]: The skill interacts with external web content, presenting a surface for indirect prompt injection. Ingestion points: pwcli open in SKILL.md. Boundary markers: None. Capability inventory: pwcli eval and pwcli run-code in references/cli.md. Sanitization: Standard browser isolation provided by Playwright.
Audit Metadata
Risk Level
SAFE
Analyzed
May 5, 2026, 04:02 PM
Security Audit — agent-trust-hub — playwright