playwright-expert
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious instructions, obfuscation, or dangerous execution patterns were detected across the skill files. Analysis of the reference materials and workflow confirms the skill serves its stated purpose of assisting with Playwright browser automation.- [SAFE]: The skill uses well-known GitHub Actions and standard npm commands for Playwright setup, which are considered safe for CI/CD environments. Credentials found in documentation are clear placeholders for local testing.- [PROMPT_INJECTION]: The skill identifies a potential indirect prompt injection surface as it interacts with external web content during automation.
- Ingestion points: Browser page content and API responses handled in references/api-mocking.md and references/debugging-flaky.md.
- Boundary markers: Not specified in the provided reference snippets.
- Capability inventory: Shell execution of Playwright tests as shown in references/configuration.md.
- Sanitization: None identified; the skill focuses on functional testing guidance rather than input sanitization.
Audit Metadata