spark-recipe-notification-hygiene

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

• Third-party content exposure detected (high risk: 0.70). The skill's Step 2 explicitly instructs the agent to read email threads using "spark thread " (SKILL.md), which ingests untrusted, third-party user-generated email content from external senders that the agent must interpret to decide actions like reclassification, grouping, or archiving.