novu-inbox-integration
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill documentation describes a pattern that allows the ingestion of untrusted HTML content into an application's DOM, which creates a Cross-Site Scripting (XSS) vulnerability surface.
- Ingestion points: The
subjectandbodyfields of notification objects, which are retrieved from external triggers and rendered via theInboxcomponent or custom render props in the client application (documented inSKILL.mdandreferences/personalization.md). - Boundary markers: The documentation instructs developers to disable the 'Disable content sanitization' toggle within the Novu workflow editor to enable HTML support, which removes the default security boundaries for notification content.
- Capability inventory: The skill uses React and Next.js components to render external data; the documented use of
dangerouslySetInnerHTMLprovides the mechanism for potential execution of malicious scripts embedded in notification payloads. - Sanitization: The skill identifies that Novu provides default sanitization but gives explicit instructions on how to bypass it for specific use cases, recommending that developers only do so if they fully control the trigger payload.
Audit Metadata