imap-smtp-email

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill includes examples that pass secrets verbatim (e.g., --token '<AUTH_TOKEN>' on the command line and plaintext IMAP_PASS/SMTP_PASS in .env), so an agent following it would need to handle and emit secret values directly.

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

• Third-party content exposure detected (high risk: 1.00). The skill's imap.js (and the documented inbox-check/inbox-fetch/inbox-download commands in SKILL.md) connects to external IMAP servers (e.g., imap.gmail.com, imap.qq.com) and parses email bodies and attachments—untrusted, user-generated third‑party content that the agent ingests and returns/acts on as part of its workflow, enabling indirect prompt injection.