ClawHub
Back to skill

Security audit

Tmp.DbhQ3VzvhJ

Security checks across malware telemetry and agentic risk

Overview

This skill transparently connects to a user's Kia account for vehicle status and confirmed vehicle actions, with sensitive credential and token handling clearly disclosed.

Install only if you trust this MCP server with your Kia account, vehicle location, and any enabled vehicle controls. Use KIA_WRITE_MODE=none for read-only access, comfort for climate and charging, and all only if you intentionally want door lock/unlock available. Protect the Kia password and exported refresh token like full vehicle-access credentials.

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 (1)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger includes a broad catch-all phrase ('any request to read or command a Kia vehicle'), which can cause the skill to activate on loosely related prompts without sufficient specificity. In this skill, unintended activation is more sensitive than usual because the skill exposes vehicle location, lock state, and real-world control actions such as climate, charging, and door lock/unlock, increasing the chance of accidental invocation and privacy-impacting or safety-relevant actions.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.