ClawHub
Back to skill

Security audit

peaq Robotics

Security checks across malware telemetry and agentic risk

Overview

The skill is a disclosed helper for operating an existing peaq ROS 2 workspace, with no hidden transfers, exfiltration, installer, or destructive behavior found.

Install only if you want an agent to operate an already-built peaq ROS 2 workspace. Review DID, storage, access-control, and background node actions before approving them, avoid passing secrets in JSON payloads, and stop launched ROS nodes when finished.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill exposes meaningful capabilities such as shell execution, file reads, and network-facing ROS 2/service interactions without declaring corresponding permissions. That weakens reviewability and policy enforcement because operators may approve the skill based on incomplete capability metadata while it can still perform sensitive runtime actions.

Tp4

High
Category
MCP Tool Poisoning
Confidence
82% confidence
Finding
The documented purpose understates the actual operational scope: beyond a simple core runtime helper, the skill can manage lifecycle transitions, expose wallet/address-related information, generate funding-request material, and perform specialized identity workflows. Description/behavior gaps are dangerous because users and approval systems may authorize a broader-power skill than they intended, especially in robotics where node control and identity/access operations can affect live systems.

Description-Behavior Mismatch

Medium
Confidence
92% confidence
Finding
This function introduces wallet funding-request behavior that is outside the declared scope of the skill, which is limited to ROS 2 runtime operations and DID/storage/access-control services. Even though it only prints a funding request line and does not directly transfer funds, adding financial workflow capability to an operational robotics skill increases the chance of misuse, deceptive prompting, or operator confusion about what the skill is authorized to do.

Context-Inappropriate Capability

Medium
Confidence
90% confidence
Finding
The file contains a funding-related capability that is not justified by the stated purpose of running an existing peaq ROS2 workspace. In a robotics control context, hidden or unexpected finance-adjacent features are risky because they can be socially engineered into broader agent flows, leak wallet metadata such as addresses, and expand the attack surface beyond what operators expect from the skill.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.