打车助手

Security checks across malware telemetry and agentic risk

Overview

This ride-booking skill is coherent for car service use, but it exposes booking and cancellation actions without a clear confirmation or privacy boundary.

Install only if you trust the publisher and your agent environment requires explicit user approval before booking, scheduling, sharing, invoicing, or cancelling rides. Treat entered locations, flight numbers, contacts, and invoice details as sensitive data that may be shared with external car-service platforms.

SkillSpector

By NVIDIA
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 (2)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly requires calling real external car-service platform APIs and handles trip details, locations, flight numbers, and sharing contacts, but it does not clearly warn users that this sensitive travel and personal data will be transmitted to third parties. This creates a real privacy and consent risk because users may disclose sensitive itinerary and contact information without understanding external sharing.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The adapter exposes state-changing operations such as request_ride, schedule_ride, book_airport_transfer, and cancel_order directly through call_function with no built-in confirmation, user-consent checkpoint, or safety guard. In an agent setting, this creates a real risk of unintended bookings or cancellations caused by model error, prompt injection, or ambiguous user input, leading to financial loss and disruption of travel plans.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal