Security audit

MongoDB Atlas

Security checks across malware telemetry and agentic risk

Overview

This is a coherent MongoDB Atlas API helper that can make real administrative changes only when the user provides Atlas credentials and approves risky calls.

Install only if you want an agent to browse and potentially operate your MongoDB Atlas Admin API. Use a least-privilege Atlas service account, keep ATLAS_API_BASE_URL unset unless you trust the endpoint, prefer read-only calls, require dry-run previews for changes, and approve --yes only after checking the exact method, endpoint, and JSON body.

SkillSpector

By NVIDIA

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.env_credential_access, suspicious.potential_exfiltration

Environment variable access combined with network send.

Critical

Code: suspicious.env_credential_access
Location: scripts/atlas-call.mjs:68

Sensitive-looking file read is paired with a network send.

Warn

Code: suspicious.potential_exfiltration
Location: scripts/atlas-call.mjs:34