gmail-reply

Warn

Audited by Snyk on Feb 25, 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 explicitly fetches and parses users' incoming emails from arbitrary external senders via the Gmail API (see "Step 1: Fetch Emails" in SKILL.md and list_unread_messages / get_message_details in references/gmail-api.md), and those untrusted, user-generated email bodies are read and used to draft replies that influence actions, so they could carry indirect prompt-injection instructions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 25, 2026, 10:49 AM