extract-email-actions-to-reminders

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly instructs the agent to "Replace {{PLACEHOLDER}} values with actual credentials from the key store," which requires embedding secret values into generated commands/code (even though scripts mention env vars), 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 Procedure explicitly instructs scanning the user's Mail library for .emlx email files (Step 1) and parsing their bodies to detect action items that directly drive creation/prioritization of reminders, so untrusted third-party email content is ingested and can influence agent actions.