playwright-expert
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- Data Exposure & Exfiltration (SAFE): The configuration examples in
references/configuration.mduse generic placeholder credentials (e.g., 'user@test.com', 'password'). These are standard placeholders and do not constitute a sensitive data leak. - Unverifiable Dependencies & Remote Code Execution (SAFE): The skill references official Playwright tools and GitHub Actions. These originate from trusted sources (Microsoft/GitHub) and follow industry-standard practices for CI/CD setup.
- Indirect Prompt Injection (SAFE): Although the skill enables browser automation which interacts with external web content, this is the primary intended purpose. The risk is mitigated by the specialized nature of the role (E2E testing) and the absence of instructions to process or trust the content of external pages beyond testing assertions.
Audit Metadata