nano-banana-pro-seeding-image

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill explicitly mentions passing an API key via the --api-key CLI flag (and shows examples of CLI usage), which would require the LLM to place the secret verbatim into generated commands if the user supplies it, creating an exfiltration risk.

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow ingests outsider-authored free text via the --prompt CLI argument and sends it as prompt in the POST to the AI Hive openapi/v1/generation/image endpoint (and optionally chat/text).