nano-banana

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

• Third-party content exposure detected (low risk: 0.10). The required workflow fetches and ingests an external documentation page from https://www.pixazo.ai/models/nano-banana.md during execution.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the agent to fetch external documentation (https://www.pixazo.ai/models/nano-banana.md) at runtime to obtain parameter names and schema details, creating an inbound operational dependency on an unverified third-party URL.