daily-briefing

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

• Third-party content exposure detected (high risk: 0.90). The skill's Execution Flow (SKILL.md Step 1) explicitly ingests external calendar events, unread emails from opportunity contacts, CRM data, and "Enrichment" signals/news on accounts — untrusted/user-generated third-party content the agent reads and uses to prioritize actions, so those inputs could carry indirect prompt-injection instructions.