ClawHub
Back to skill

Security audit

hazmat-disposal-router

Security checks for vulnerabilities and agentic risk

Overview

This skill provides offline household hazardous-waste guidance and does not request unusual access or perform hidden actions.

This appears safe to install for offline disposal-routing help. Treat its location-specific guidance as a starting point and confirm accepted items, local rules, and facility hours with your municipality before transporting hazardous materials.

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)

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

The documentation explicitly states the skill is offline, but elsewhere in the same file it presents 'channel finders' for US/EU/UK and instructs users to 'find your local channels' and confirm local facility hours. That creates an intent contradiction within the skill documentation: a truly offline stdlib tool cannot directly find locality-specific facilities or current hours unless it embeds a static directory, which is not described here.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.