ClawHub
Back to skill

Security audit

Uptime Tool

Security checks for vulnerabilities and agentic risk

Overview

This skill appears low-risk: it only reads local uptime, but its documentation overstates the features it actually provides.

Before installing, treat this as a simple Linux uptime helper, not a full monitoring tool. It may not support the advertised command-line options or cross-platform behavior unless the publisher adds the missing implementation.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The declared description says the skill shows multiple system health metrics: uptime, load average, active user count, and boot time. The supplied code only reads /proc/uptime and prints a formatted uptime duration. It does not access or report load average, user count, or boot time. There are no undeclared dangerous capabilities, but the implementation materially under-delivers relative to the declared primary behavior, so this is a description-behavior mismatch.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.