sutochno

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

• Third-party content exposure detected (high risk: 0.75). Yes—at runtime the skill navigates to Sutochno city pages (outsider-authored public web content) and extracts listing text via page.evaluate(EXTRACT_JS), which is then returned as JSON fields (e.g., name, area) and thus fed into the agent’s LLM context.