prospect-research

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s required runtime workflow fetches and web-researches a prospect’s public footprint from a user-provided LinkedIn URL and multiple external sources, meaning outsider-authored free text is ingested (e.g., profile content, posts, articles, podcasts/transcripts, and X posts) for quote extraction and synthesis.