browser-agent

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly requires stepwise actions that include typing plaintext credentials (e.g., "password123", "secret", "admin@test.com") into form fields as literal strings in the agent's instructions, which forces the LLM to emit secret values verbatim and creates an exfiltration risk.