Back to skill

Security audit

EasyEDA Agent

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill suspicious with high confidence because it reports an unverified installer that runs a downloaded script and several confirmed weaknesses in design-editing and verification workflows; some scanner coverage is incomplete.

Consider avoiding installation until the installer can be independently verified and the reported design-workflow weaknesses and incomplete scan coverage have been reviewed. If you proceed, understand that the scan does not establish malicious intent, but it also cannot confirm that all referenced content was fully inspected.

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
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (49)

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 24)May include surrounding context.

md
求解器、样例或模型生成的数据均须满足[数据契约](references/schematic-data.md#数据驱动架构基准);不强制某个求解器。

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 63)May include surrounding context.

md
| 原理图数据、布局与 Apply | [数据契约](references/schematic-data.md)、[执行步骤](references/auto-layout-sop.md) |

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 45)May include surrounding context.

md
完成前按[布局规则](references/pcb-layout.md)通过连续两轮自检,第二轮包含保存重载和新回读;修复后重来。

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 66)May include surrounding context.

md
| PCB 布局与机械 | [PCB](references/pcb.md)、[布局](references/pcb-layout.md) |

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 62)May include surrounding context.

md
| 需求、选型与设计取舍 | [设计流程](references/design-flow.md)、[决策参考](references/design-decisions.md)、[器件选型](references/part-selection.md) |

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 69)May include surrounding context.

md
| 库器件或自建库 | [选型](references/part-selection.md)、[建库](references/library-authoring.md)、[候选表](references/standard-parts.json) |

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 64)May include surrounding context.

md
| 原理图检查或局部修复 | [原理图](references/schematic.md)、[放置](references/schematic-placement.md)、[连接](references/schematic-wiring.md) |

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 66)May include surrounding context.

md
| PCB 布局与机械 | [PCB](references/pcb.md)、[布局](references/pcb-layout.md) |

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 72)May include surrounding context.

md
| 由已有 PCB 生成 3D 打印外壳(上下壳/推盖、开孔、螺丝柱、卡扣) | [参数化外壳](references/pcb.md#参数化外壳离线生成-stl) |

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 67)May include surrounding context.

md
| PCB 布线、铺铜与禁布区 | [布线](references/pcb-routing.md) |

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 73)May include surrounding context.

md
| 连接、升级或保存异常 | [环境配置](references/environment-setup.md)、[Action 边界](references/actions.md) |

Chaining Abuse

High
Category
Tool Misuse
Confidence
98% confidence
Finding

Piping the network response directly into bash converts remotely supplied bytes into executable instructions without a verification boundary. This is the same bootstrap supply-chain exposure identified by SC2, rather than separate evidence of malicious chaining, but it can still yield arbitrary execution under the user's account.

Content

Scanner excerpt · references/environment-setup.md (reported line 58)May include surrounding context.

发布版安装 CLI 和 Skill:

bash
curl -fsSL https://raw.githubusercontent.com/zhoushoujianwork/easyeda-agent/main/install.sh | bash
easyeda update --check
easyeda update

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
75% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · references/pcb-layout.md (reported line 408)May include surrounding context.

md
irst** (reports paths/lines/arcs WITHOUT mutating — safe on any board, even one you don't want to change), then run for real and `pcb save`. Flags: `--selected` (only tracks selected in EasyEDA, default whole board), `--net` (**repeatable** — `--net USB_DP --net USB_DM` beautifies only those nets; the safest way to apply on a dense board — small blast radius, dry-run + DRC each net), `--layer` filter, `--force-arc` (round even too-short segments), `--merge-u` (fuse tight U-bends into one arc), `--no-protect`/`--no-drc`/`--no-pour-rebuild`. **On a dense, not-yet-DRC-clean board prefer per-net over a full-board pass** — a whole-board run both has a large blast radius and surfaces the board's pre-existing violations alongside its own. Absorbed from the open-source **Easy_EDA_PCB_Beautify** (m-RNA, Apache-2.0; see repo `NOTICE`). Line-width bezier smoothing is a documented follow-up. Advice from upstream: pad-to-track joints may need a manual look, exclude RF/high-speed nets from a global

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
75% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · references/reusable-module-library.md (reported line 48)May include surrounding context.

md
### 从已完成原理图直接提取

优先使用现场 `sch read --no-check` 的制造网表,不再从 PDF 重猜连接;再用 `lib by-lcsc`
将每个供应商编号解析成 32 位 Device UUID。公开 `*.topology.json` 必须把原位号转换为模块内
角色、把匿名网改为 `internal.*`、把跨模块网改为 `port.*`,并保留全部物理引脚。只有
`sch read.floatingPins` 明确列出的脚才能记录为 `connectionState:"unconnected"`;字段缺失不能

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, file_read, file_write, network, shell.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.