gtm-get-better

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

• Third-party content exposure detected (high risk: 0.85). The workflow ingests outsider-authored free text from cold-email replies polled from the user’s Gmail via /gtm-cold-email --check-replies, which writes reply bodies into outreach-log/email-replies.jsonl and then classifies that text with the agent’s LLM (indirect prompt-injection risk).