ClawHub
Back to skill

Security audit

Linux & service basics

Security checks for vulnerabilities and agentic risk

Overview

This Linux service troubleshooting skill includes some administrative repair commands, but they are disclosed, purpose-aligned, and gated on user approval.

Install this only if you want the agent to help diagnose and, when you approve it, suggest or run Linux service administration commands. Review any commands involving systemctl, Nginx reloads, chmod/chown, or systemd service creation before applying them on a production server.

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)

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The manifest describes the skill as diagnosing Linux service issues using logs, service managers, reverse proxy checks, and DNS sanity checks. The command systemctl reload nginx performs a state-changing administrative action rather than a purely diagnostic check, which goes beyond the described troubleshooting/inspection scope.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.