inbox-commander

Fail

Audited by Snyk on Feb 19, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 0.80). The skill instructs the agent to include original email content in forwards/drafts and to "present wallet/payment details from invoice," which requires reproducing potentially sensitive values (bank details, payment addresses, or other secrets) verbatim in its output.

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

  • Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches and reads the user's Gmail Inbox (Execution Flow step 4 "Fetch emails") and later parses and acts on untrusted third-party email content (e.g., Invoice/Bill Handling reads invoice bodies and payment links, Bulk Unsubscribe opens external unsubscribe URLs), so arbitrary external emails could supply instructions that materially influence actions.
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 19, 2026, 01:21 AM