ClawHub
Back to skill

Security audit

Auto Dealership Car Service Kit

Security checks across malware telemetry and agentic risk

Overview

This is a content-only automotive marketing skill, but it includes review-gating and targeted outreach patterns that users should review carefully before use.

Install only if you are prepared to treat the outputs as draft marketing copy, not guaranteed compliant campaigns. Remove or avoid the review-gating language, confirm consent and opt-out handling before any email/SMS/CRM/custom-audience use, and have legal or compliance review all public ads, review requests, financing claims, and retargeting workflows before publishing.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (3)

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The prompt explicitly instructs a gated review flow: customers predicted to give 5 stars are sent to Google, while dissatisfied customers are diverted to private feedback. That is a deceptive review-manipulation pattern that can violate platform rules and consumer-review expectations, distort public reputation signals, and expose the business to policy enforcement or regulatory scrutiny. In this context, the skill is specifically designed for reputation management, which makes the issue more dangerous because it operationalizes the practice as a reusable workflow.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The prompt authorizes a very broad set of advertising, CRM, nurture, follow-up, and conquest-marketing tasks without clear guardrails on when the skill should be invoked or what data/use constraints apply. In practice this can cause overbroad activation and generation of high-risk marketing content, including regulated claims, aggressive targeting, or outreach workflows in contexts the user did not specifically authorize.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The prompt explicitly supports CRM data use, website visitor retargeting, custom audiences, and follow-up messaging, but does not require any privacy notice, consent validation, lawful basis check, or platform-policy verification. This creates a real risk of producing campaigns that misuse personal data, violate CAN-SPAM/TCPA/privacy laws, or encourage impermissible audience targeting and retargeting practices.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.