reports-morning-briefing

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and parses user-generated content (Slack messages via slack_search_public_and_private, Gmail unread threads, Fireflies transcripts, and related Jira/Calendar lookups) as required runtime inputs to synthesize action items and decisions, so untrusted third-party content can materially influence the agent's outputs and behavior.