Mcp Client

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward MCP client whose remote tool, resource, and API-key behavior is disclosed and aligned with its purpose.

Install only if you intend to connect an agent to MCP servers. Use trusted HTTPS server URLs, use least-privilege API keys, inspect exposed tools and resources before calling them, and treat server-provided prompts or resources as untrusted unless you control the server.

SkillSpector

By NVIDIA

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
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)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 95% confidence
Finding: The skill exposes clear network and MCP integration capabilities but does not declare corresponding permissions or constraints. That mismatch can bypass user/operator expectations and policy controls, making it easier for the skill to connect to external services and access sensitive resources without explicit review.

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The skill is described in broad terms as able to connect to MCP servers, invoke tools, and read resources, with few hard boundaries on when or how it should be used. In this context, that is dangerous because MCP can expose remote tools and file/resource reads, so an agent could be induced to interact with untrusted servers or sensitive data sources more easily than intended.

VirusTotal

54/54 vendors flagged this skill as clean.

View on VirusTotal