email-tools

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill shows and encourages embedding app passwords directly in configuration files and in a curl command-line (--user "you@gmail.com:app-password"), which requires the LLM/agent to handle and output secret values verbatim, creating an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to read messages from third-party IMAP/SMTP servers (e.g., himalaya configured to imap.gmail.com and examples like "himalaya read 123 | summarize"), so untrusted, user-generated email content is fetched and processed and could influence replies or downstream tool actions.