Back to skill

Security audit

Ping

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed local network diagnostic tool, but users should be aware it can scan small subnets and retain local history.

Install only if you are comfortable with a local tool that records ping, traceroute, monitor, compare, and sweep results under ~/.ping. Use the sweep command only on networks you are authorized to probe, and be careful with PING_OUTPUT because it writes exports to the path you provide.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (5)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The declared purpose suggests simple ping/traceroute troubleshooting, but the documented behavior also includes subnet sweeping, persistent history collection, configurable exports, and config management. This mismatch is dangerous because users or orchestration systems may authorize the skill for low-risk diagnostics while it actually enables host discovery, broader reconnaissance, and arbitrary-path output writes.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
96% confidence
Finding

The skill advertises shell execution, environment-variable control, and local file writes but does not declare any tool scope or permissions boundary. In an agent ecosystem, this can lead to overbroad execution authority, making it easier for the skill to run network commands and write files without explicit user or platform consent.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill description presents a troubleshooting tool for ping and traceroute, but the implementation includes subnet host discovery plus broader local data management features such as history export and mutable configuration. This scope expansion increases abuse potential because an operator could use the skill for internal network enumeration and data extraction beyond the narrowly declared purpose, reducing transparency and informed consent.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The sweep command performs active host discovery across a CIDR range using concurrent probing, which is materially different from single-host connectivity troubleshooting. In many environments this is a sensitive reconnaissance capability that can be misused for internal network mapping, trigger monitoring alerts, or violate least-privilege expectations for a simple ping utility.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The skill stores historical ping results and configuration under ~/.ping/, but the documentation does not prominently warn about retention, sensitivity, or lifecycle of those records. Even if the data is local, it can reveal internal hosts, monitoring targets, and operational patterns that may be sensitive on shared or managed systems.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.