mail

Warn

Audited by Snyk on Mar 16, 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). This skill calls the Gmail API (see skill-router.json baseUrl "https://gmail.googleapis.com" and SKILL.md actions "list-threads" / "get-thread") to fetch user email threads and message snippets, which are untrusted, user-generated content the agent reads and could use to drive replies or other actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 16, 2026, 11:25 AM
Issues
1