novu-design-workflow
Pass
Audited by Gen Agent Trust Hub on May 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides technical documentation and design patterns for notification workflows. No malicious patterns, such as unauthorized command execution, credential harvesting, or multi-layer obfuscation, were detected.- [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection as it describes processing untrusted
payloaddata within workflow steps. - Ingestion points: Untrusted event data enters the context via
payload.*variables (e.g.,payload.webhookUrl,payload.userId) documented inreferences/workflow-templates.mdandreferences/step-conditions.md. - Boundary markers: No specific delimiters or "ignore instructions" markers are defined for the interpolated payload data.
- Capability inventory: The workflow design includes the capability to perform network operations through
HTTP Requeststeps (step.http), as seen in Templates 8 and 9. - Sanitization: The documentation does not specify server-side validation or sanitization for these user-defined payload variables, relying on the platform's default handling.
Audit Metadata