umbraco-chrome-navigation

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill explicitly tells the agent to "log in by setting the username/password inputs" (e.g., using __umb.fill(value)), which would require the LLM to emit user credentials verbatim into tool calls/outputs, creating a secret-exfiltration risk.