ez-google-imagen

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly instructs using an API key via a --api-key argument (including examples with "your-api-key-here") and tells the agent to use an API key if provided in chat, which requires the LLM to accept and emit secret values verbatim in commands—an exfiltration risk.