ai-artist

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

• Third-party content exposure detected (high risk: 0.90). The skill's included reference files explicitly instruct the agent to use web search tools and grounding (e.g., references/advanced-techniques.md "Agent Prompting" lists search(query) and directs "Wait for result before continuing", and references/nano-banana.md mentions "Search Grounding: tools=[{"google_search": {}}]"), which means the agent is expected to fetch and interpret open web content that could be untrusted.