playwright-verifier

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements read-only verification workflows using legitimate testing frameworks.
  • [EXTERNAL_DOWNLOADS]: The skill provides links to authoritative documentation and rule repositories from well-known organizations including the W3C, Microsoft (Playwright), and Deque Systems (axe-core).
  • [PROMPT_INJECTION]: The skill includes an attack surface for indirect prompt injection by processing external web content from a user-provided URL. This is inherent to the tool's function as a web verifier.
  • Ingestion points: The url and selector parameters in SKILL.md.
  • Boundary markers: Not explicitly defined in the provided instructions.
  • Capability inventory: Utilizes Playwright for browser interaction and element inspection.
  • Sanitization: No specific sanitization or filtering logic is mentioned for the ingested DOM content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 05:34 AM
Security Audit — agent-trust-hub — playwright-verifier