ClawHub
Back to skill

Security audit

HK Nearby Facilities

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently finds nearby Hong Kong public toilets using disclosed official FEHD data and does not show hidden persistence, credential access, or destructive behavior.

Before installing, understand that the skill may contact FEHD government endpoints when used and may process a place name or coordinates you provide to rank nearby facilities. It appears narrowly scoped, but the hardcoded example install path may need adjustment in another environment.

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
  • 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 (1)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill invokes a bundled Python script that fetches official FEHD endpoints, which means it has network capability, but the manifest does not declare any explicit tool scope such as permissions or allowed-tools. This creates a policy and review gap: callers may not realize the skill performs outbound network access, and future changes could expand remote interactions without an explicit security boundary.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.