mongodb-atlas-checker
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides templates and guidance for secure MongoDB Atlas configuration, explicitly recommending against hardcoding credentials in source code and environment variable examples.
- [SAFE]: All scripts and code samples provided in the reference guide use standard, industry-recognized libraries (mongoose, mongodb) and follow established development patterns for database connectivity and error handling.
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it is designed to analyze project-specific documentation and source code which are external, untrusted inputs.
- Ingestion points: The agent is instructed to scan files such as
.agents/SYSTEM/ARCHITECTURE.mdand existing database configuration files within the user's project. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to disregard natural language instructions that might be embedded within the analyzed project files.
- Capability inventory: The skill includes a connection verification script (
scripts/test-mongodb-connection.ts) that performs network operations to connect to a database. - Sanitization: No sanitization or validation logic is present for the content extracted from project documentation or source code.
Audit Metadata