semantic-model-authoring
Warn
Audited by Snyk on Jul 30, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The skill’s required runtime workflow for Fabric semantic model inspection/validation (e.g., “Connect & inventory” and “Test new measures” via executeQueries/getDefinition) ingests the semantic model’s stored DAX text and error/trace details from the target workspace via Fabric/Power BI REST APIs, which can include outsider-authored content (e.g., code/metadata submitted by other users in that workspace).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata