The Agent Skills Directory

Prompt Injection (SAFE): The skill contains no instructions designed to bypass safety filters or override system prompts. All instructions are focused on software testing best practices.\n- Data Exposure & Exfiltration (SAFE): There are no patterns suggesting access to sensitive files, environment variables, or unauthorized network communication.\n- Remote Code Execution (SAFE): The skill references standard CLI commands like npx playwright, which are common in development environments. No malicious remote scripts or piped execution patterns (e.g., curl|bash) are present.\n- Persistence and Privilege Escalation (SAFE): No attempts to modify system configurations, scheduled tasks, or acquire administrative privileges were found.

Playwright Skill