product-showcase

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly shows and encourages passing credentials on the command line for authenticated captures (e.g., --auth user:password) and workflows that would require the agent to embed user/passwords or tokens verbatim in commands or scripts, which risks secret exfiltration.

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md workflow requires the agent to browse and capture arbitrary app URLs provided in "Gather Input" and "Capture Screenshots" (e.g., using Chrome MCP / Playwright on https://app.example.com or http://localhost:5173), meaning the agent will fetch and interpret untrusted third‑party web content as part of its generation workflow.