email-skill

Warn

Audited by Snyk on Mar 21, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The skill's "personal" provider explicitly uses IMAP/SMTP (imap-smtp-email/scripts/imap.js and related inbox-* commands in SKILL.md and email_gateway.sh) to fetch and read arbitrary user emails and attachments from external senders, so the agent will ingest untrusted, user-generated third-party content and act on it (search, fetch, download, forward), enabling indirect prompt injection.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 21, 2026, 04:45 PM
Issues
1