Back to skill

Security audit

PCB设计助手

Security checks for vulnerabilities and agentic risk

Overview

This PCB design skill is coherent, but it should be reviewed because it can drive exec-backed EDA automation and generate manufacturing files by default without an explicit confirmation step.

Install this only if you want an agent to actively operate on EasyEDA/JLCPCB PCB projects. Before use, require explicit confirmation for any EDA project mutation, Gerber/BOM/CPL export, or ordering-related step, and keep JLCPCB credentials or tokens in local config only, never in chat or generated files.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger keywords include very broad terms such as 'pcb', 'eda', 'bom', and 'schematic', which are common in normal engineering discussions. This can cause the skill to activate outside clear user intent and, in this skill's case, may lead an agent toward exec-enabled design automation or production-output workflows when the user only wanted discussion or advice.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill defaults to producing BOM/CPL/Gerber/assembly outputs and elsewhere declares use of exec and bridge/API actions, but the user-facing description around deliverables does not prominently warn that executable actions and manufacturing-ready artifacts may be generated. In a hardware-design context, silent or unexpected generation/export increases the chance of unintended file creation, project modification, or manufacturing submission workflows being initiated from ambiguous prompts.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
73% confidence
Finding

The skill name and summary are presented in Chinese, and the document is largely written to operate in a Chinese EasyEDA/JLCPCB context, but it does not explicitly offer the user a language or locale choice. This can be a natural-language policy issue when a skill implicitly forces one language experience without opt-in.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The skill documents configuration of a JLCPCB API token in a local config path but provides no privacy or secret-handling warning. This can normalize exposing or mishandling credentials in prompts, logs, screenshots, or generated diagnostics, increasing the risk of credential leakage even if the token is only optionally used.

Content

No source excerpt is available for this finding.