agent-email-cli

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

• Third-party content exposure detected (high risk: 0.75). The required workflow runs the agent-email CLI (e.g., agent-email read ... --full / agent-email show ...) which ingests mailbox message bodies authored by external senders, and those message texts can be included in the LLM context via the agent’s summarization/extraction of command output.