skills/mengto/skills/playwright/Gen Agent Trust Hub

playwright

Pass

Audited by Gen Agent Trust Hub on Jul 8, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes npx to fetch the @playwright/cli package from the official npm registry. This is a standard method for using well-known browser automation tools from a trusted vendor.
  • [COMMAND_EXECUTION]: A local bash script (scripts/playwright_cli.sh) is used to execute the Playwright CLI. The script correctly handles process execution and argument passing.
  • [PROMPT_INJECTION]: The skill facilitates browsing external websites and processing their content, which creates a potential surface for indirect prompt injection.
  • Ingestion points: Commands like open and snapshot in SKILL.md and scripts/playwright_cli.sh.
  • Boundary markers: None.
  • Capability inventory: Filesystem writes to output/playwright/ (screenshots, PDFs, and traces) and browser-based network access.
  • Sanitization: The skill does not implement specific filtering or sanitization of the DOM content retrieved during snapshots.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 8, 2026, 08:35 AM
Security Audit — agent-trust-hub — playwright