Back to skill

Security audit

AUBO Robot

Security checks for vulnerabilities and agentic risk

Overview

This is a real robot-control skill with disclosed purpose, but it exposes physical motion and IO control without enough safety scoping, validation, or operator controls.

Review carefully before installing on any machine connected to a real robot. Use only in a controlled robotics environment with a trained operator, emergency stop available, cleared workspace, explicit confirmation before motion or IO, validated speed and workspace limits, and known-safe SDK provenance. Treat the current status/telemetry methods as unreliable until they parse real controller responses.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (3)

T09 · Insecure Skill Coding Practices

Error
Location
aubo_openclaw_driver.py:212
Finding

Safety-Critical Robot Motion Commands Lack Input and Operational-State Validation

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
aubo_openclaw_driver.py:254
Finding

Digital Output Pin Is Used in a Bit Mask Without Bounds Validation

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Warning
Location
SKILL.md:86
Finding

Unpinned and Inconsistently Declared Third-Party SDK Dependency

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (9)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
95% confidence
Finding

The package explicitly advertises robot motion capabilities such as joint, linear, circular, speed, and stop control, but provides no visible safety warning, operator prerequisites, workspace hazard notice, or limits on physical actuation. In a robotics skill, omission of physical-world safety guidance materially increases the risk of unsafe deployment, unintended motion, collision, or operator injury, especially because the package also includes a default robot host and claims the skill is ready and tested.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This documentation exposes motion and IO control capabilities for an industrial/collaborative robot but does not include any safety warning, safe-operating prerequisites, simulator-only cautions, or real-hardware hazard guidance. In this context, readers may directly execute movement examples or IO operations on physical equipment, creating risk of unintended motion, collision, pinch/crush hazards, or unsafe actuator activation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This file contains natural-language descriptions, docstrings, and runtime print messages exclusively in Chinese, including the skill description used for registration. Under the policy, forcing a specific language without opt-in or justification is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The status APIs advertise live robot state but return hardcoded placeholder values like [0.0] * 6 or a default mode instead of validated telemetry. In a robot-control skill, false state can directly mislead upstream automation, safety checks, or operators into issuing unsafe motion commands based on nonexistent feedback, making this more dangerous than an ordinary correctness bug.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The declared capabilities list omits available control functions such as speed control and stop-related behavior exposed by the driver. This creates a transparency and policy-enforcement gap: platforms or reviewers may approve the skill for a narrower control surface than it actually provides, which is especially risky in a physical robot context where undisclosed actuation changes the trust boundary.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

This manifest describes a robot-control skill with capabilities for motion, IO control, and real hardware interaction, but it does not define any trigger scope, operator confirmation requirement, or invocation constraints. In a robotics context, ambiguous activation boundaries materially increase the chance of unintended or unauthorized motion commands being exposed to users or downstream agents, which can lead to physical safety incidents or equipment damage.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The file's natural-language instructions and descriptions are presented in Chinese throughout, and there is no indication that users may opt into another language or that the skill is intentionally restricted to a Chinese-speaking or region-specific audience. Under the language/locale policy, forcing a specific language without user opt-in is a policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

Multiple user-facing manifest fields, including the description, warnings, commands, and notes, are presented in Chinese, but the file does not state that the skill is intended only for Chinese-speaking users or offer an alternative language option. This can violate language/locale policy when users have not explicitly opted into that locale.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The package description uses Chinese text exclusively, which can impose a specific language on users without any opt-in or explanation. The file does not indicate that the skill is intentionally limited to a Chinese-speaking audience or provide multilingual alternatives.

Content

No source excerpt is available for this finding.