Wake On Lan

• Outcome: Pass
• Latest audit: Sep 11, 2026 · 7:59 AM UTC
• Version: 1.0.0

Overview

This skill is a straightforward Wake-on-LAN helper that sends local network wake packets and stores a disclosed device list.

Install only if you want an agent to send Wake-on-LAN packets on your local network and maintain a saved device list under ~/.config/openclaw/wol-devices.json. Review saved devices before using broadcast, and prefer explicit Wake-on-LAN phrasing to avoid ambiguous commands.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Rogue Agent: Self-Modification, Session Persistence
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration

Findings (7)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 93% confidence
• Finding: The skill describes shell-capable behavior via installation and command execution patterns but does not declare any tool scope such as allowed-tools or permissions. This weakens enforcement and review because an agent may invoke shell actions without an explicit least-privilege contract, increasing the chance of unintended command execution.

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The trigger phrase "wake" is extremely generic and can match ordinary user intent unrelated to Wake-on-LAN, causing accidental invocation of this skill. Unintended activation matters here because the skill can send network packets and modify persistent device configuration, so a simple conversational phrase could trigger side effects.

Vague Triggers

Medium

• Confidence: 87% confidence
• Finding: The documented commands are highly generic (for example, list, add, remove, status, broadcast) and lack namespace or scope constraints, making them prone to collision with unrelated skills or normal assistant actions. Because these commands can alter saved configuration and send network-wide wake traffic, ambiguous routing could produce unintended state changes or network actions.

Session Persistence

Medium

• Category: Rogue Agent

Content

# Install wakeonlan tool
brew install wakeonlan

# The skill will automatically create config at:
# ~/.config/openclaw/wol-devices.json
```

• Confidence: 60% confidence
• Finding: Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Description-Behavior Mismatch

Medium

• Confidence: 93% confidence
• Finding: The manifest describes Wake-on-LAN functionality for waking devices by MAC address or name, which reasonably covers sending WoL packets and looking up names. However, the script also adds/removes/list devices in a persistent config file and performs status checks with ping, which extends beyond the stated wake-only behavior into local device management and network reachability monitoring.

Missing User Warnings

Low

• Confidence: 84% confidence
• Finding: This markdown file states that the skill will automatically manage a device configuration file and later exposes add/remove and broadcast operations, but it does not include an explicit warning that the skill writes to a local config file and can send Wake-on-LAN packets to all saved devices on the local network. For a user-facing skill description, those behaviors can affect local data and networked systems and should be disclosed clearly.

Context-Inappropriate Capability

Low

• Confidence: 81% confidence
• Finding: A Wake-on-LAN skill is expected to send magic packets to wake hosts, but actively probing devices with ping is a separate network-scanning/status capability. Because the manifest only mentions waking devices remotely by MAC address or name, the status-check behavior is not explicitly within the declared purpose.

Static analysis

No suspicious patterns detected.