ClawHub
Back to skill

Security audit

check charger availbility

Security checks for vulnerabilities and agentic risk

Overview

This skill checks EV charger availability and includes a clearly documented optional notification helper that writes small local state files.

Before installing, provide a Google Places API key only if you trust the publisher with charger lookup usage, and only enable cron notifications if you want recurring checks that store last-seen availability in your local cache.

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 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 (1)

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding
The skill is presented as a simple EV charger availability checker, but the bundled documentation also describes a notification helper that persists state in ~/.cache/charger-notify and performs change-based alerting. That is a real capability expansion beyond the declared purpose, and undeclared stateful behavior can mislead operators, complicate review, and create trust and permission-boundary issues even if the functionality itself is not overtly malicious.

Static analysis

No suspicious patterns detected.