ClawHub
Back to skill

Security audit

旅行预算规划师

Security checks across malware telemetry and agentic risk

Overview

This is a local Chinese travel-budget helper with no evidence of credential access, network calls, persistence, or hidden side effects.

Install this if you want a Chinese-language, offline travel budget estimator using static reference prices. Treat the estimates as rough planning data, not live prices, and note that the advertised destination coverage appears overstated.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Description-Behavior Mismatch

Low
Confidence
96% confidence
Finding
The manifest description says the skill can estimate budgets for '20+热门目的地', implying coverage of at least 20 destinations. The hardcoded DESTINATIONS table in the code defines 19 destinations, so the implemented coverage does not fully match the advertised capability.

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
This code file contains user-facing natural-language descriptions and outputs in Chinese only, beginning with the module docstring and continuing throughout the tool's interface. Under the policy rule, forcing a specific language without user opt-in is a natural-language policy violation.

Natural-Language Policy Violations

Medium
Confidence
93% confidence
Finding
The generated budget report and CLI error/help messages are presented only in Chinese, with no mechanism for users to choose another language. Because the skill exposes natural-language output directly to users, this is a locale policy issue rather than a code-style preference.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.