exploring-scouts

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

• Third-party content exposure detected (medium risk: 0.30). In SKILL.md the required runtime workflow for this “exploring signals scouts” skill reads and renders free-text fields that are derived from scout session transcripts and reports (e.g., scout-runs-retrieve/tasks-runs-session-logs-retrieve summaries and tool inputs/agent narration, and inbox-reports-retrieve report contents via emitted_report_ids / edited_report_ids), where those transcripts and report bodies can be influenced by outsider-authored data present in the monitored project signals.