inbox-triage

Warn

Audited by Snyk on Mar 30, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs the agent to list and read unread emails via third‑party inbox access (e.g., "Prerequisites" Option A: Gmail via gmailctl or Option B: IMAP via himalaya and the note "This skill reads emails"), so arbitrary external/user-generated email content is ingested and used to triage, draft replies, and make archive/alert decisions, allowing untrusted content to influence actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 30, 2026, 12:22 AM
Issues
1