Ping

• Outcome: Pass
• Latest audit: May 29, 2026, 8:24 PM
• Version:
  1.0.0

Overview

This is a disclosed network diagnostic skill that can scan user-selected subnets and saves results locally, so it should be used only on networks the user is authorized to test.

Install only if you need local network diagnostics. Use sweep only on networks you own or are authorized to test, and remember that hostnames, IP addresses, route previews, and sweep results are saved under ~/.ping unless you delete or protect that directory.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration

Findings (5)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 93% confidence
• Finding: The skill advertises executable shell commands, environment-variable inputs, and file writes, but declares no permissions or trust boundaries. That creates a real security issue because an agent or user may invoke network operations and write persistent data without explicit approval, increasing the chance of unintended command execution, data persistence, or policy bypass.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 90% confidence
• Finding: The documented purpose is simple connectivity troubleshooting, but the described behavior expands into subnet sweeping, persistent history collection, exports, and configuration management. This mismatch is dangerous because it can cause users or orchestration systems to grant trust appropriate for a diagnostic ping tool while the skill also performs host discovery and ongoing data collection, which materially broadens security and privacy impact.

Description-Behavior Mismatch

Medium

• Confidence: 93% confidence
• Finding: The skill description says it is for connectivity troubleshooting with ping and traceroute, but the implementation also performs subnet sweeping and broader multi-target comparison/history/export operations. That scope expansion matters because subnet host discovery is an active reconnaissance capability that can be used for internal network mapping beyond ordinary diagnostics.

Context-Inappropriate Capability

Medium

• Confidence: 96% confidence
• Finding: The sweep command actively enumerates hosts in a CIDR range and reports alive systems, which is network discovery rather than simple host reachability testing. In an agent skill context this increases misuse risk because it enables reconnaissance against a local or reachable network segment with little friction.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The subnet sweep probes up to 256 hosts concurrently and stores discovered live hosts to history without any user warning that it is scanning a network or persisting results. This can surprise users, create unauthorized scanning activity, and leave a local inventory of internal hosts that may be sensitive.

VirusTotal

66/66 vendors flagged this skill as clean.