e2e-testing

Pass

Audited by Gen Agent Trust Hub on May 4, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exposes a surface for indirect prompt injection because its primary function involves reviewing and potentially executing user-provided test files.
  • Ingestion points: User-provided E2E tests, spec files, and integration tests intended for writing, fixing, or review (SKILL.md).
  • Boundary markers: No boundary markers or specific instructions are provided to isolate user-provided code from the agent's internal instructions.
  • Capability inventory: The skill provides instructions to execute shell commands using npx playwright test (SKILL.md).
  • Sanitization: There are no documented procedures for sanitizing or validating user-provided test content before it is processed or executed.
  • [SAFE]: The skill correctly manages sensitive data by instructing the agent to read credentials from environment variables (process.env.OPENAI_API_KEY) instead of hardcoding them.
  • [SAFE]: All referenced scripts, helpers, and configurations are located within the project's local directory structure, and the toolset used (Playwright) is a standard industry framework.
Audit Metadata
Risk Level
SAFE
Analyzed
May 4, 2026, 07:34 AM