playwright-test
Pass
Audited by Gen Agent Trust Hub on Jun 24, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
Bashtool to executepnpmcommands for running Playwright tests (pnpm --filter=@posthog/playwright exec playwright test). This is a standard operation for test automation suites. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data that could contain malicious instructions.
- Ingestion points: The skill reads
@playwright/README.mdand navigates to web pages using browser tools (mcp__playwright__browser_navigate). - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the prompt when processing these external sources.
- Capability inventory: The skill has access to
Bash(shell execution),Write/Edit(file system modification), and browser interaction tools. - Sanitization: No specific sanitization or validation of the README content or web page text is mentioned before processing.
Audit Metadata