z-mail-reader

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt includes an example that passes the IMAP authorization code directly on the command line (python3 ... --auth-code "YOUR_CODE"), which requires the agent to accept and/or emit the secret value verbatim and is therefore high-risk secret handling.

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

• Third-party content exposure detected (medium risk: 0.30). scripts/listen_emails.py triggers scripts/read_emails.py which logs into the configured IMAP mailbox and reads outsider-authored email bodies/headers to generate JSON and write sum.md (including subject/from/body_preview and image extraction from mail HTML).