content-research-writer

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

• Third-party content exposure detected (medium risk: 0.65). The skill’s runtime “Research Assistance” step can fetch and extract information from public web pages/URLs supplied by the user, and that fetched free-form page text is then ingested into the agent’s LLM context (public web content category via runtime browsing/scraping).