playwright-test

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOWSAFE
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill defines a surface for indirect prompt injection by instructing the agent to read and follow patterns from a local handbook file and user input.
  • Ingestion points: openmetadata-ui/src/main/resources/ui/playwright/PLAYWRIGHT_DEVELOPER_HANDBOOK.md and user-supplied scenarios in the /playwright-test command.
  • Boundary markers: None present to delimit user/file data from system instructions.
  • Capability inventory: The skill is restricted to code generation and display. No subprocess execution, file-write, or network capabilities are defined in the skill file.
  • Sanitization: No input validation or sanitization is performed on the ingested content.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 01:19 PM