playwright-expert
Pass
Audited by Gen Agent Trust Hub on Aug 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructional content and code templates for Playwright testing. No malicious patterns, obfuscation, or unauthorized network behaviors were detected.\n- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill correctly demonstrates the use of environment variables for sensitive URLs and references 'auth.json' for authentication state persistence. These are standard, documented practices within the Playwright framework for managing test environments securely.\n- [INDIRECT_PROMPT_INJECTION]: The skill possesses a standard attack surface for indirect prompt injection common to coding assistants that process user-provided specifications.\n
- Ingestion points: User-defined test requirements and application flow descriptions provided during the agent interaction (SKILL.md).\n
- Boundary markers: None explicitly defined in the provided instructions.\n
- Capability inventory: Generation of test scripts, configuration files, and suggested execution of Playwright CLI commands.\n
- Sanitization: No specific sanitization logic is included; the skill relies on the underlying LLM's safety guardrails.
Audit Metadata