Security audit

设计

Security checks for vulnerabilities and agentic risk

Overview

This MongoDB skill is not malicious, but it asks for broad execution and write authority for database automation without clear guardrails.

Review this skill before installing. Use it only with explicit instructions, least-privilege database credentials, and non-production or backed-up environments unless you manually approve each command or database change.

SkillSpector

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
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

Findings (2)

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The skill’s scope and activation conditions are vague, describing broad capabilities like schema design, queries, configuration, and workflow automation without clear boundaries or allowed/disallowed actions. In an agent environment with read/exec/write tools, ambiguous invocation criteria can cause the model to apply the skill in unintended contexts and take actions beyond what a user expected, increasing the risk of unsafe command execution or configuration changes.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The documentation explicitly classifies the skill as "MD+execute()" and the metadata grants exec capability, but it does not warn about host-side effects such as file modification, process execution, environment exposure, or unintended system changes. Because this is an automation/integration skill with broad workflow language, users and agents may invoke execution paths without understanding the operational risk, making misuse or accidental damage more likely.

Static analysis

No suspicious patterns detected.