email-to-tasks

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill explicitly asks for the email/thread "verbatim" and requires every task to quote its source line, which forces the LLM to reproduce any secrets present in the email content verbatim in its output.

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s required runtime workflow ingests the “email/thread” input verbatim to extract quoted requests and drafts a confirming reply (“verbatim; extraction quotes its sources”), which means outsider-authored free text delivered via an email thread is directly consumed.