ai-app

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

• Third-party content exposure detected (high risk: 0.90). The skill’s examples and workflow (see references/chatbot.md "Web Search Chatbot" and agent examples) explicitly use Perplexity (perplexity('sonar-pro')) and OpenAI web-search tools to fetch public web/search results (rendered as source-url parts) which the agent ingests and uses to form responses and drive tool behavior, exposing it to untrusted third‑party content.