imapflow

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill includes hardcoded authentication fields (plain-text password and OAuth access-token examples like 'password', 'ya29.xxx...', 'oauth2-token') which require the LLM to handle or reproduce secret values verbatim, creating an exfiltration risk.

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

• Third-party content exposure detected (medium risk: 0.30). Outsider-authored email content becomes readable at runtime when the required workflow uses ImapFlow to fetch messages (e.g., fetchOne(..., { source: true }) / fetch(...) and streams msg.source, msg.text, or decoded parts after a mailbox is selected and IDLE triggers new message events).