ClawHub
Back to skill

Security audit

Pilot Clipboard

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple Pilot Protocol clipboard helper whose network sharing behavior is disclosed and aligned with its purpose, though users should review content before sending it.

Install this only if you trust your Pilot destinations and understand that anything you pipe or pass into these commands may be sent over the Pilot network. Review clipboard contents and command output before sending, and avoid secrets, credentials, regulated data, or private project details unless sharing is explicitly authorized.

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
93% confidence
Finding

The skill explicitly demonstrates sending arbitrary clipboard contents and command output to a remote destination over the Pilot network, but it provides no warning, consent step, sensitivity guidance, or destination validation. This creates a realistic risk of accidental exfiltration of secrets, tokens, internal commands, or host data, especially because the examples encourage piping live command output directly into network transmission.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.