desktop-workflow-generator

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly asks for credentials or Playwright storageState and shows embedding them into Playwright CLI fill commands and inline JS (e.g., fill "{value}", const state = ), which forces the LLM to output secret values verbatim.

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

• Third-party content exposure detected (high risk: 0.90). The skill requires the agent to navigate to and interact with an arbitrary app URL provided by the user (Phase 4: "Please provide the URL" and Phase 5: live Playwright walkthrough), capturing and interpreting page content/screenshots to decide actions and verifications, which clearly ingests untrusted third‑party web content that can materially influence subsequent tool use.