ClawHub
Back to skill

Security audit

HK Parking Meter Finder

Security checks for vulnerabilities and agentic risk

Overview

This skill fetches official Hong Kong parking-meter datasets to answer parking availability questions, and its network use is disclosed and purpose-aligned.

Before installing, expect the skill to run a Python script that contacts official Hong Kong government data endpoints to retrieve current parking-meter information. It does not appear to access credentials or persist data, but users who require strict network allowlisting should restrict it to the documented DATA.GOV.HK resource endpoints.

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
  • 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 (2)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding

The skill instructs the agent to run a bundled Python script that consumes live official datasets, implying network access, but the skill manifest does not declare any explicit tool scope or allowed-tools restriction. That mismatch can cause the agent runtime to grant broader-than-intended execution/network capability or make the skill's external access invisible to policy enforcement and review.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/hk_metered_parking.py (reported line 29)May include surrounding context.

python
def fetch_text(url: str) -> str:
    req = urllib.request.Request(url, headers={"User-Agent": UA, "Referer": "https://data.gov.hk/"})
    with urllib.request.urlopen(req, timeout=60) as resp:
        return resp.read().decode("utf-8-sig", "ignore")

Static analysis

No suspicious patterns detected.