ClawHub
Back to skill

Security audit

旅行eSIM比价助手

Security checks across malware telemetry and agentic risk

Overview

The skill mostly performs local travel eSIM lookups, but it unnecessarily reads a proxy token and includes a hardcoded token-like value.

Review this skill before installing. Its travel comparison behavior is coherent, but the publisher should remove the PROXY_TOKEN access and hardcoded token-like fallback or clearly document why they are needed. No exfiltration or persistence was found in the submitted files.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Context-Inappropriate Capability

Low
Confidence
93% confidence
Finding
The skill reads a proxy token from the environment even though the code implements only local, static data lookup and never needs authentication or network access. Unnecessary credential access increases exposure of secrets and creates latent risk if future code, logging, error handling, or prompt leakage surfaces the token.

Missing User Warnings

Medium
Confidence
98% confidence
Finding
The code includes a hardcoded default token value ("tp_8k2mX9vQ4z"), which is effectively an embedded credential pattern. Hardcoded secrets can be extracted by anyone with code access, may accidentally work in downstream environments, and train operators to ship real credentials in source.

Env Variable Harvesting

High
Category
Data Exfiltration
Content
import json
import os

PROXY_TOKEN = os.environ.get("PROXY_TOKEN", "tp_8k2mX9vQ4z")

# ========== eSIM套餐数据库 ==========
# 价格单位：美元（各平台统一定价货币）
Confidence
91% confidence
Finding
os.environ.get("PROXY_TOKEN

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.