content-repurposing

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

• Third-party content exposure detected (high risk: 0.75). The skill’s workflow explicitly allows “Gather source material: URLs, transcripts, posts, or research report” and “it can also start directly from URLs,” which implies runtime ingestion of outsider-authored free text from public web pages or other non-user sources into the LLM context via URL/transcript extraction.