mapbox-style-quality
Warn
Audited by Snyk on Feb 15, 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 explicitly instructs ingesting and validating GeoJSON from "user uploads" and "external APIs" (see "When adding GeoJSON data" and "GeoJSON Validation" sections), meaning the agent would read and interpret arbitrary third-party/user-generated content that could carry indirect prompt injection.
Audit Metadata