Deep Agents Memory & Filesystem

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt includes tools that read and return stored values verbatim (e.g., get_user_preference returns result.value and save_user_preference echoes f"Saved {key}={value}"), which can cause the agent to output secrets or credentials in plain text.