Lead Research Assistant

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime workflow for “Research [Company Name]” / “Recent news” implies fetching and summarizing public web sources (e.g., company news pages, press releases, review sites like G2/Glassdoor) whose body text is outsider-authored and becomes LLM-readable context via the research/summarization step.