audience-belief-mapper

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 ingests outsider-authored free text directly from the user-provided “interview transcripts, win-loss notes, sales-call summaries, and support tickets,” which can include arbitrary malicious strings submitted by a non-trusted user into those inputs without selecting a specific item first.