gmail-label
Warn
Audited by Snyk on Mar 27, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches user emails via SKILL.md "Step 1: Fetch emails" and scripts/gmail_label_fetch.py, writes them to .tmp/chunks, and spawns the email-classifier subagent (SKILL.md Step 3) to read those untrusted, user-generated email snippets and make labeling decisions that are then applied via the Gmail API, so third‑party content can directly influence agent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata