ClawHub
Back to skill

Security audit

汽车经销商客诉话术生成器

Security checks for vulnerabilities and agentic risk

Overview

This skill is a markdown-only dealership complaint response helper with no code execution or persistence, though users should avoid pasting unnecessary personal or internal records.

Before installing or using this skill, treat it as a drafting aid for complaint-handling language. Do not paste full contracts, IDs, phone numbers, VINs, complete chat logs, or other sensitive customer/internal records unless necessary and authorized; use placeholders where possible.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
88% confidence
Finding

The skill instructs users to collect, summarize, and circulate customer names, complaint details, contracts, work orders, communication logs, and platform/channel information without any warning or minimization guidance for personal or internal data. In a dealership complaint-handling context, this can lead to unnecessary exposure of customer PII and sensitive internal records in model prompts, generated outputs, or broader staff sharing.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.