Back to skill

Security audit

郑州科威莱步进电机控制器调试助手-雄安素水公司编写

Security checks for vulnerabilities and agentic risk

Overview

This skill is a clear motor-controller helper, but it can directly move physical hardware and change controller settings without enough safety gating or fail-safe handling.

Review this carefully before installing or using it with real equipment. Use it only with supervised hardware, tested limit switches, an independent emergency stop, and your own validation around travel limits, speed, communication errors, and confirmation before any movement or controller-setting write.

Vulnerability Patterns
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (5)

T09 · Insecure Skill Coding Practices

Error
Location
python_driver.py:391
Finding

Communication failures are interpreted as successful motion completion in the PC driver

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
micropython_driver.py:433
Finding

Communication failures are interpreted as successful motion completion in the MicroPython driver

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
python_driver.py:411
Finding

PC motion operations can start with stale or mechanically unsafe parameters

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
micropython_driver.py:453
Finding

MicroPython motion operations can start with stale, wrapped, or mechanically unsafe parameters

Content
View full analysis
> 8) & 0xFF, addr & 0xFF, (value >> 8) & 0xFF, value & 0xFF ]) ``` ### Technical Analysis Failures from `set_direction()` and `set_speed()` are ignored. The method can consequently issue a run command with stale settings left in the controller. `set_angle()` and `set_distance_mm()` do not reject negative or oversized values. In the MicroPython implementation, right shifts and `& 0xFF` masking serialize only the low 16 bits. This can transform out-of-range o ...[truncated 1213 chars]
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
micropython_driver.py:174
Finding

MicroPython driver incompletely validates Modbus read and write responses

Content
View full analysis
> 8) & 0xFF, addr & 0xFF, (value >> 8) & 0xFF, value & 0xFF ]) crc = self._calculate_crc16(frame) frame.append(crc & 0xFF) frame.append((crc >> 8) & 0xFF) response = self._send_request(frame) if not response or len(response) < 8: return False if response[0] != self.device_addr or response[1] != 0x06: return False if not self._verify_crc(response): return False return True ``` ### Technical Analysis For function code `0x03`, the response byte count should equal `count * 2`, and the complete frame length should equal `3 + byte_count + 2`. Neither property is enforced. An odd or inconsistent byte count can also cause an out-of-range access at `data_bytes[i+1]`. For function code `0x06`, Modbus requires the successful response to echo the requested register address and value. The implementation does not compare bytes 2-5 with the request. A valid CRC response for the same device and function, including a stale response for another write, can theref ...[truncated 1560 chars]
Remediation
View remediation
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (9)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly states that all code supports reading or writing any register on a motor controller, including registers for motion start, direction, homing, speed, and emergency stop. In a hardware-control context, unrestricted write guidance can directly cause unintended physical movement or unsafe state changes, and the document does not clearly require confirmation, authorization, or a prominent safety warning before such actions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

These methods perform real-world motor movement, homing, and emergency-stop-driven positioning against a physical limit switch without prominently warning callers that invoking them causes immediate actuator motion. In a hardware-control library, unclear safety semantics can lead to unexpected movement during testing or integration, creating pinch, collision, or equipment-damage risk if developers call the API without proper guarding, interlocks, or operator awareness.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The convenience API move_mm immediately sets direction, speed, distance, and starts the motor, but its documentation does not clearly emphasize that calling it initiates physical motion. Convenience wrappers are especially risky because they reduce friction and may be invoked casually by application code, increasing the chance of unintended movement, operator surprise, or mechanical damage.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This driver exposes callable methods that directly issue motion, homing, and emergency-stop related Modbus writes to physical hardware without any built-in safety interlocks, confirmation gates, authorization checks, or operator-presence safeguards. In a skill/agent context, these methods could be invoked programmatically and cause unexpected physical movement or re-homing of attached machinery, creating equipment damage or operator safety risks if called at the wrong time or with unsafe parameters.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file presents the skill name, instructions, and operational guidance only in Chinese. Under the stated policy, forcing a specific language without offering user choice or documenting a justified locale constraint is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The manifest presents the skill name and description only in Chinese, with no natural-language indication that the skill is China-region-specific or that users may choose another language. Under the policy rule, a skill that effectively forces a specific language without opt-in can be a locale-policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

This markdown file is entirely presented in Chinese from the title onward, with no indication that users may choose another language or locale. Under the policy rule for natural-language violations, a skill or documentation artifact that effectively imposes a language without opt-in can be flagged when no alternative or justification is provided.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

All user-facing natural language in comments, docstrings, and printed output is Chinese, which effectively forces a specific language for users of the skill. The file does not provide an opt-in language choice or explain that the skill is intentionally limited to a Chinese-speaking or region-specific audience.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

Natural-language content throughout the module, including the top-level description, docstrings, and printed status messages, is entirely in Chinese with no alternative locale or opt-in mechanism. This can violate language/locale policy when users are not explicitly given a choice or informed that the skill is region/language-specific.

Content

No source excerpt is available for this finding.