Security audit

Mongo Manager Free

Security checks across malware telemetry and agentic risk

Overview

This MongoDB skill needs Review because it mixes guide content with broad live database operation authority and lacks clear safety controls before using command execution or database credentials.

Install only if you are comfortable with an agent using command execution around MongoDB. Use least-privilege or read-only database credentials by default, avoid production connection strings, and require explicit confirmation before any create, update, delete, import, export, save, or index-changing action.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands

Findings (7)

Description-Behavior Mismatch

Medium

Confidence: 95% confidence
Finding: The manifest and description frame the skill as a documentation/guide resource, but the body claims active CRUD, import/export, and runtime operation support. This mismatch can cause an agent or user to invoke the skill in a higher-risk operational context than expected, increasing the chance of unintended database modification or data exfiltration.

Description-Behavior Mismatch

Medium

Confidence: 93% confidence
Finding: The manifest says the skill is not suitable for database architecture decisions, yet the content promotes schema design as a primary use case. This inconsistency undermines safe routing and trust boundaries, making it more likely that agents rely on the skill in contexts the manifest says to avoid.

Intent-Code Divergence

Medium

Confidence: 91% confidence
Finding: The capability coverage statement broadly asserts support for all described scenarios, including areas the manifest excludes. Such self-attestation of broad support can mislead an agent into over-trusting the skill's competence and invoking it outside its intended safety envelope.

Vague Triggers

High

Confidence: 97% confidence
Finding: The manifest's trigger scope is overly broad, covering generic database, SQL, and data storage tasks despite the skill being MongoDB-focused. In an agent ecosystem, this can cause inappropriate auto-selection for unrelated tasks, exposing credentials, data, or execution pathways in contexts the skill was not designed to handle.

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The capability coverage section uses sprawling keyword fragments as activation cues without clear boundaries, which can manipulate routing or matching heuristics. This increases the chance of accidental invocation and unsafe use in contexts far beyond a MongoDB optimization guide.

Missing User Warnings

Medium

Confidence: 96% confidence
Finding: The skill describes create, modify, delete, save, import, and export operations without any user-facing warning, confirmation step, or safety guard. In a skill with exec capability and database context, this creates a real risk of destructive changes or unauthorized data movement being performed implicitly.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The skill advertises exec-based operation and environment-based database connectivity without clearly warning users about command execution, credential exposure, and privacy risks. In context, this is more dangerous because it targets databases and may operate with live connection strings, making unintended execution materially harmful.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.