Back to skill

Security audit

Ai-Thinker-Coder

Security checks for vulnerabilities and agentic risk

Overview

This is a hardware-development guide skill with expected, user-directed setup and firmware flashing instructions, but users should be careful before flashing connected devices.

Before installing, confirm this skill matches your Ai-Thinker hardware workflow. Do not run firmware flashing commands until you have selected the correct serial port and target board and are ready to overwrite firmware on the connected device. Review any external SDK repository before building or flashing it.

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The README gives direct firmware flashing commands (make flash) without warning that this operation writes to the connected device and may erase or overwrite existing firmware. In a hardware-development skill, users may copy-paste commands blindly, which can lead to accidental loss of device state, custom firmware, calibration data, or temporary device unavailability.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The directory structure explicitly labels the main entry as Chinese and this README is also a Chinese installation guide, while the document does not state that language selection is optional or explain a region-specific requirement. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
82% confidence
Finding

This markdown file presents the skill description and usage instructions in Chinese throughout, which can effectively force a specific language for users unless they discover alternate documentation. The policy allows locale constraints only when clearly documented and justified or when the user is given a language choice, which is not stated in the skill file itself.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The structure section states SKILL.md is the main entry in Chinese, which suggests a default language constraint for core skill content. There is no accompanying note that users can select English or another language when using the skill.

Content

No source excerpt is available for this finding.