ClawHub
Back to skill

Security audit

差旅打车

Security checks for vulnerabilities and agentic risk

Overview

This car-service skill is not malware-like, but it can present simulated rides, drivers, prices, and cancellations as if they were real bookings.

Review before installing. Do not rely on this skill for real transportation, invoices, driver details, or cancellations unless the publisher adds a real authenticated provider integration, clear enterprise-only scope, and a user confirmation step before booking or canceling rides.

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
90% confidence
Finding
The adapter directly exposes state-changing operations such as ride booking and order cancellation and executes them immediately once a function call is made. In an LLM-agent setting, this creates a real risk of unintended purchases or cancellations from prompt injection, misunderstanding, or ambiguous user intent because there is no explicit confirmation gate in code before invoking the backend service.

Static analysis

No suspicious patterns detected.