nano-banana-artist

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow explicitly instructs the agent to perform web research using Perplexity ("Research Current Trends" in SKILL.md step 2) and to use Google Search for "search grounding" (references/prompt-templates.md), which clearly fetches open/public third-party content that the agent is expected to read and use to influence prompting and generation decisions, creating risk of indirect prompt injection.