ClawHub
Back to skill

Security audit

Allow your claws to do things remotely on a Desktop machine via MCP

Security checks for vulnerabilities and agentic risk

Overview

This skill openly provides remote machine control, which is powerful but coherent with its stated purpose and disclosed security controls.

Install only when you intend to let an agent operate the configured remote machine. Use least-privilege permissions.json policies, restrict allowed IPs and hosts, protect the bearer token, and be careful with command execution, file delete/move/write actions, and logged-in browser sessions.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This skill explicitly advertises full remote machine control, including command execution and file read/write, but the user-facing description does not prominently warn about the destructive and sensitive impact of those capabilities. In a skill that can act on a remote host, weak or missing impact warnings increase the chance of accidental misuse, unauthorized destructive actions, or unintended access to sensitive data.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.