ClawHub
Back to skill

Security audit

ToneClone CLI

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward ToneClone CLI helper, with a privacy caution because prompts may include conversation and relationship context sent to the service.

Before installing, confirm you trust ToneClone and avoid putting secrets, regulated data, or unnecessary private conversation history into prompts. Use only the minimum context needed for the writing task, especially for work, client, medical, legal, or financial content.

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
Confidence
94% confidence
Finding
The skill explicitly encourages users to include thread history, background details, and recipient relationship context in prompts sent to an external CLI/service, but provides no warning about privacy, data handling, or minimization. This can lead users to disclose sensitive personal, business, or third-party information to a remote service unnecessarily, increasing confidentiality and compliance risk.

Static analysis

No suspicious patterns detected.