JAKA Robotics Control Skill

• Outcome: Review
• Latest audit: May 29, 2026 at 9:29 PM UTC
• Version:
  1.0.1

Overview

This appears to be a legitimate JAKA robot-control skill, but it can enable and move real hardware without enough built-in safety gates.

Install only if you intentionally want local scripts or an agent to control a real JAKA robot. Use a trusted SDK source, test in simulation or reduced-speed/manual mode first, verify the work area is clear and the emergency stop works, and require human approval before enablement, motion, homing, or I/O commands.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Missing User Warnings

High

• Confidence: 94% confidence
• Finding: The README provides copyable examples that connect to a physical robot, enable it, and issue joint and linear motion commands without any explicit safety prerequisites such as verifying a clear workspace, confirming protective stops/E-stop readiness, or warning that motion can cause injury or equipment damage. In a robotics-control skill, documentation is part of the operational interface; omitting these warnings materially increases the chance of unsafe real-world actuation by users following the quick-start steps.

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The script connects to a physical robot, enables it, and proceeds toward motion-related operations without any explicit runtime safety warning, interlock check, or user confirmation that physical movement may occur. In robotics contexts, immediate execution against a real controller can cause unsafe motion in a shared workspace, making the lack of operator acknowledgment materially dangerous.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The movement sequence issues joint and linear motion commands as part of a demonstration script, but the code does not clearly warn that it will move the robot in physical space or require confirmation before those commands are sent. Because the skill targets a real robot IP and performs repeated motion, the context makes this more dangerous than a generic example script: a user may run it expecting a harmless test and trigger unintended physical motion.

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The CLI directly executes digital output state changes from user input without any confirmation, warning, authorization gate, or safety interlock visible at this layer. In a robot-control context, changing I/O can energize tooling, actuate peripherals, or alter safety-relevant signals, so accidental or scripted misuse could cause unsafe physical behavior.

VirusTotal

63/63 vendors flagged this skill as clean.