spark-recipe-invitation-manager

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly instructs the agent to fetch and read email invitation threads from the user's Inbox (e.g., "spark emails Inbox --filter 'category:invitation'" and "spark thread "), which ingests untrusted, user-generated third-party content and uses it to drive decisions like accept/decline/reschedule.