testing-e2e

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill's OrchestKit analysis flow and E2E examples (e.g., tests and pages in examples/orchestkit-e2e-tests.md and HomePage.submitUrl) explicitly accept and analyze arbitrary URLs like "https://example.com/..." so the agent runtime is expected to fetch and interpret untrusted third‑party web content to produce artifacts and agent-driven decisions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). Flagged the .mcp.json entry that runs "npx -y @playwright/mcp@latest" because this npx invocation fetches and executes remote npm package code at runtime (used as the required MCP server for the AI agent workflow).