Android Device Automation

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes examples that embed secrets verbatim (e.g., .env API key placeholders and an act example that fills a password like 'pass123' in the prompt), which encourages the LLM to emit or relay secret values directly in commands or prompts and thus creates an exfiltration risk.