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 public news headlines for tracked topics (see "Gather the data" and "News" in SKILL.md) and requires the agent to read/interpret those third‑party items to produce "why it matters" and to influence the dashboard and the "Today's one thing" decision, so untrusted external content can materially affect agent behavior.