travel-customizer

Security checks across malware telemetry and agentic risk

Overview

This skill does what it says: it collects confirmed travel inquiry details and saves them to a configured Feishu table, with privacy controls left to the installer.

Install this only if you intend to store customer travel inquiries in Feishu. Use a dedicated least-privilege Feishu app, restrict access to the destination table, and tell users before submission that their contact and travel details will be stored there, including your retention and deletion practices.

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 (3)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The README explicitly states that personal travel request data will be collected through conversation and stored in Feishu, but it does not clearly warn users that their data is transmitted to and retained in a third-party platform. This creates a privacy and consent gap: users may disclose names, phone numbers, travel dates, budgets, and special needs without understanding the storage destination, retention, or access scope.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The function transmits personally identifiable and potentially sensitive travel details, including name, phone number, destination, dates, budget, and special requirements, to a third-party SaaS platform without any in-code indication of user notice or consent gating. In a skill context, silent export of user data to an external service increases privacy and compliance risk even if the destination is legitimate.

External Transmission

Medium
Category
Data Exfiltration
Content
"records": [{"fields": fields}]
        }
        
        resp = requests.post(url, headers=headers, json=payload, timeout=10)
        resp.raise_for_status()
        result = resp.json()
Confidence
86% confidence
Finding
requests.post(url, headers=headers, json=

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal