enterprise-user-management-ai-system
Warn
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The installation instructions direct users to clone a repository from an unverified GitHub account (
Nareshkumar2583/Enterprise-User-Management-System-with-AI-Analytics.git). This introduces a dependency on unverified external code that is not maintained by a trusted organization or the skill author. - [COMMAND_EXECUTION]: The skill instructs the agent/user to execute setup commands (
npm install,pip install,npm start,uvicorn main:app) on the content of the cloned repository. This sequence results in the execution of third-party code from an unverified source. - [INDIRECT_PROMPT_INJECTION]: The application described by the skill ingests and processes untrusted user data which is later passed to AI analytics services.
- Ingestion points: Data enters the system through task creation (
POST /api/tasks), support tickets (POST /api/tickets), and user profile updates, which are then processed by analytics endpoints inSKILL.md. - Boundary markers: The provided code snippets do not show any use of delimiters or instructions to ignore embedded commands when passing data to the ML service or LLM components.
- Capability inventory: The system has capabilities to perform database operations (MongoDB), manage user authentication (JWT), and return AI-generated risk and burnout assessments.
- Sanitization: There is no evidence of sanitization, escaping, or validation of user-provided strings before they are utilized by the AI logic in the backend or ML service.
Audit Metadata