playwright
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides structured guidelines and code templates for developing Playwright tests, using standard industry patterns.
- [SAFE]: Credentials in code examples are benign placeholders (e.g., 'user@test.com', 'pass123').
- [COMMAND_EXECUTION]: The skill includes standard CLI commands for running Playwright tests via 'npx'.
- [INDIRECT_PROMPT_INJECTION]: The defined workflow for exploring and interacting with web pages introduces a surface for indirect prompt injection. 1. Ingestion points: Target page content and snapshots (SKILL.md). 2. Boundary markers: Absent for web content analysis. 3. Capability inventory: File modification (Edit, Write), network access (WebFetch), and command execution (Bash). 4. Sanitization: None specified for web data processing.
Audit Metadata