mongodb-atlas-checker
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- Indirect Prompt Injection (SAFE): The skill identifies a potential injection surface by instructing the agent to scan project documentation (e.g., ARCHITECTURE.md) for context. Evidence: 1. Ingestion points: references/full-guide.md. 2. Boundary markers: Absent. 3. Capability inventory: Local diagnostic auditing. 4. Sanitization: Absent. Note: This is a standard architectural discovery pattern for development agents.
- Data Exposure & Exfiltration (SAFE): The skill handles sensitive environment variables like MONGODB_URI but follows security best practices by discouraging hardcoding and advising on proper .env usage. No exfiltration patterns detected.
- External Downloads (SAFE): Recommended packages (mongoose, mongodb, dotenv, ts-node) are standard, reputable libraries required for database connectivity.
Audit Metadata