ClawHub

MongoDB Skill - 灵活的文档数据库管理

Security checks across malware telemetry and agentic risk

Overview

This MongoDB skill is not malicious, but it needs review because it teaches powerful database-changing operations without enough safety boundaries.

Install only if you are comfortable reviewing generated MongoDB commands before use. Use read-only or least-privilege database accounts by default, avoid production databases for exploratory prompts, keep credentials out of prompts and shell history, and require explicit confirmation plus backup or matched-count review before any bulk update, delete, index drop, restore, or schema-changing action.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Vague Triggers

Medium
Confidence
86% confidence
Finding
The skill description says it should activate when users mention broad terms like "MongoDB, NoSQL, 文档数据库," which can cause the skill to engage on generic database discussions rather than explicit requests to manage MongoDB. Overly broad activation increases the chance the agent will produce database-specific operational guidance or commands in contexts where the user did not intend to invoke this skill, raising the risk of unsafe or irrelevant actions.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
This section provides direct examples for bulk and destructive document modifications such as updateMany across broad filters, field additions to all documents, and array mutations, but it does not require confirmation, scope validation, dry-run review, or backup recommendations adjacent to those actions. In an agent setting that translates natural language into operational commands, this materially increases the likelihood of accidental mass data modification or irreversible corruption from ambiguous or mistaken user requests.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal