ClawHub
Back to skill

Security audit

alexa-mcp

Security checks for vulnerabilities and agentic risk

Overview

This Alexa skill is a disclosed smart-home control guide with confirmation gates for changes, though users should invoke it explicitly because some trigger examples are broad.

Install only if you intend to let an agent operate your Alexa-connected home and lists. Use explicit Alexa or device-control wording, and pay close attention to confirmation previews before approving changes, especially unlock, garage-door, routine, announcement, or thermostat actions.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The trigger description is broad enough to match ordinary conversational phrases like "we're away next week" or "check off eggs" without an explicit request to control Alexa. In a skill that can operate locks, garage doors, routines, announcements, and thermostats, overbroad activation increases the chance of unintended invocation and could lead to surprising or security-relevant actions if the agent routes ambiguous user input here.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.