ClawHub
Back to skill

Security audit

Coin Collection Truck 香港收銀車

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow Hong Kong coin-truck schedule helper that runs a local script over bundled schedule data, with no evidence of hidden access, persistence, exfiltration, or destructive behavior.

Before installing, understand that this skill runs a local Python script and relies on its bundled 2026 schedule data. It looks low risk from a security perspective, but users should verify important route or location details against an official source, especially because one inspected record appears to have mismatched address/coordinate data.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
Findings (3)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding

The skill instructs the agent to invoke a local Python script and references local filesystem paths, but it does not declare any explicit tool scope such as allowed-tools or permissions. This creates a policy gap where an agent may use shell or file access beyond what is transparently documented, increasing the risk of unintended local file access or broader command execution if the skill is reused in a more permissive environment.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

One schedule entry appears internally inconsistent: the district is listed as 荃灣區 (Tsuen Wan), but the English address references Tung Chung/Ying Tung Estate coordinates, indicating likely mismatched location data. In a location-and-schedule skill, this can misdirect users to the wrong district or service point, reducing trust and causing real-world navigation errors.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

This JSON file is dominated by Chinese field names and Hong Kong-specific date/address conventions, with only partial English translation. For a skill artifact, that creates an implicit language/locale restriction without any accompanying statement that the skill is Hong Kong-specific or that users can choose another language/locale.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.