geo-query-finder

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

• Third-party content exposure detected (high risk: 0.75). Outsider free text can enter the agent’s LLM context via Step 1 “Research the Brand” (web search results/pages fetched at runtime) and via Step 3 “Query ChatGPT via OpenAI Search API,” where the model’s web-search-enabled response is generated from real-time external web content.