customer-email-draft-threads

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (medium risk: 0.30). The skill instructs the assistant to repeatedly ping the user every hour until a task is confirmed resolved, which constitutes unnecessary and intrusive annoyance steering (harassment/denial-of-service style persistence).

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow inspects and processes inbound email messages from users, which is an outsider-authored free text source monitored by the agent.