monday-brief

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

• Third-party content exposure detected (high risk: 0.75). SKILL.md describes pulling data from multiple live connectors (e.g., Gmail flagged emails, Slack DMs, calendar events with external attendees) and then “show the full brief in chat”/optionally post to Slack/Teams, so outsider-authored free text from those external systems is likely ingested into the LLM context during brief generation.