ClawHub
Back to skill

Security audit

自驾出行规划

Security checks across malware telemetry and agentic risk

Overview

This travel-planning skill sends user-entered route, place, and weather queries to a disclosed cloud proxy for map data, with no evidence of hidden persistence, local data access, destructive behavior, or credential theft.

Install only if you are comfortable sending entered trip locations and city queries through the skill publisher's cloud proxy before they reach Gaode Maps. Avoid entering highly sensitive home, workplace, or private itinerary details unless you trust that proxy and its no-storage claim.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
85% confidence
Finding
The skill declares use of network access and an environment variable token (`PROXY_TOKEN`) but does not declare explicit permissions, creating a transparency and governance gap. This is dangerous because the skill sends user trip queries through a cloud proxy, and without explicit permission scoping or disclosure enforcement, users and platform controls may not fully understand or restrict external data transmission or secret use.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill sends user-supplied trip data, including origin, destination, waypoints, location queries, and city lists, to an external Tencent SCF proxy without any visible disclosure or consent flow. In a travel-planning context, this data can reveal sensitive location patterns and itinerary details, so undisclosed third-party transmission creates a real privacy and trust risk.

Env Variable Harvesting

High
Category
Data Exfiltration
Content
# ===== 代理配置 =====
GAODE_PROXY = "https://1439498936-bl10af74fl.ap-guangzhou.tencentscf.com"
PROXY_TOKEN = os.environ.get("PROXY_TOKEN", "tp_8k2mX9vQ4z")

# ===== 通用请求 =====
def _post_proxy(api_type, params):
Confidence
78% confidence
Finding
os.environ.get("PROXY_TOKEN

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.