ClawHub
Back to skill

Security audit

Node Connect

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because scanners report device-approval actions that go beyond its stated connection-diagnosis purpose; the evidence is incomplete because a local reference could not be resolved.

Review the skill’s approval behavior before installing. Install only if you need pairing approvals and are comfortable with that capability; the scan is partial because a local path-like reference could not be matched to a bundled artifact, so the evidence is incomplete.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (2)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The device-listing and node-status commands support the declared diagnostic purpose. However, openclaw devices approve <requestId> performs an authorization-changing action that the description does not disclose. The approve --latest command also contains no explicit preview or dry-run option; its inline comment alone does not establish that approval is prevented.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 102)May include surrounding context.

bash
openclaw devices list
openclaw devices approve --latest   # preview only; exits without approval
openclaw devices approve <requestId>
openclaw nodes status