playwright-expert

Pass

Audited by Gen Agent Trust Hub on Jul 29, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill documents standard end-to-end testing practices and follows established patterns for Page Object Model implementation using Playwright.
  • [PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection because it is designed to ingest and act upon external data, such as user requirements or debugging traces, which could contain malicious instructions.
  • Ingestion points: User flow requirements and browser trace files used during debugging workflows (SKILL.md).
  • Boundary markers: None explicitly defined to delimit or sanitize external data input.
  • Capability inventory: The skill is used to generate executable TypeScript test code and provides shell commands for test execution via npx (SKILL.md).
  • Sanitization: No evidence of sanitization or validation for externally provided test specifications or logs.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 29, 2026, 10:42 AM
Security Audit — agent-trust-hub — playwright-expert