NYC

playwright-e2e-tester

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOWPROMPT_INJECTIONEXTERNAL_DOWNLOADSNO_CODE
Full Analysis
  • SAFE (SAFE): No malicious code, obfuscation, or unauthorized access attempts were detected within the skill's content.
  • Indirect Prompt Injection (LOW): The capability to generate tests from user stories or acceptance criteria creates an attack surface where malicious input could influence generated code. Evidence: 1. Ingestion points: User stories and acceptance criteria (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Generation of TypeScript test scripts and YAML CI/CD configurations. 4. Sanitization: No specific sanitization or validation logic is defined for the external inputs.
  • EXTERNAL_DOWNLOADS (LOW): The CI/CD example includes commands for installing browser binaries. These are standard for Playwright and originate from a trusted source.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 04:21 AM