ClawHub
Back to skill

Security audit

SSH Connection & Execution Management

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent SSH administration guide, but it normalizes powerful remote and bulk system changes without clear approval or safety gates.

Install this only if you intend to let the agent manage real SSH targets and you trust the referenced ssh_mcp server. Before use, require explicit approval for upgrades, restarts, file changes, key imports, and bulk execution, and verify the target client, host list, maintenance window, health checks, and rollback plan.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly instructs the agent to perform remote system administration tasks such as system updates and troubleshooting over SSH, but it does not require user confirmation, change review, maintenance-window checks, or environment validation before executing impactful operations. In an agentic context, this omission is dangerous because the examples normalize direct execution of privileged remote actions across real infrastructure, increasing the chance of unintended outages or unauthorized changes.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The examples include commands like 'apt-get upgrade -y' and 'systemctl restart nginx' that can alter system state, trigger package changes, or interrupt live services, yet no warning or approval step accompanies them. Because this skill is specifically designed for persistent and bulk remote execution over SSH, such examples can be copied directly into production workflows and magnify operational risk across multiple hosts.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.