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