nano-banana-2-image-edit

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill explicitly allows passing API keys via a --api-key command-line flag and even documents the key prefix ("sk-api-*"), which encourages embedding secrets verbatim in commands or prompts and therefore creates a direct exfiltration risk.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The runtime workflow ingests outsider-authored free text via the user-supplied --prompt (and optional --system) arguments, which are sent as the prompt/messages[].content to the chat/text or generation/image OpenAPI endpoints.