ClawHub
Back to skill

Security audit

Chatbot Builder

Security checks for vulnerabilities and agentic risk

Overview

This is a simple chatbot-builder instruction file whose data-training and channel-deployment features are disclosed and purpose-aligned, though users should handle training data carefully.

Before installing or using this skill, review and minimize any documents used for training, avoid confidential or unauthorized data, and verify access controls for each deployment channel, especially public web widgets and team messaging platforms.

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
91% confidence
Finding

The skill encourages training chatbots on uploaded documents and deploying them to external messaging channels without any warning about sensitive data handling, consent, or exposure risks. This can lead users to ingest confidential information and then unintentionally surface it through public or third-party channels such as Slack, Discord, WhatsApp, or a web widget.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.