create-pom

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill automates the creation of Playwright Page Object Model (POM) files using a predefined template and standard test practices. It operates locally within the project's E2E test directory.
  • [SAFE]: No patterns of data exfiltration, hardcoded credentials, or suspicious remote downloads were found. The skill relies on standard developer tools and frameworks.
  • [PROMPT_INJECTION]: The workflow requires reading external application pages to identify locators, which creates an indirect prompt injection surface as the agent processes content from the pages being tested.
  • Ingestion points: External application pages (SKILL.md workflow).
  • Boundary markers: None present in the generation instructions.
  • Capability inventory: File system write operations for creating TypeScript files (SKILL.md).
  • Sanitization: No explicit instructions provided for sanitizing or escaping content retrieved from application pages.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 11:48 AM
Security Audit — agent-trust-hub — create-pom