action-item-extractor

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 Teams meeting chat messages (Step 2: "Get all chat messages from the Teams meeting...") — untrusted, user-generated third-party content — and the agent must read/interpret those messages (Step 3) to produce action items that drive downstream decisions, so this enables indirect prompt-injection risk.