ClawHub
Back to skill

Security audit

Pcb Design Assistant Free

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed EasyEDA/JLC schematic-design assistant with proportionate localhost bridge and command-use instructions, though its trigger wording is broader than ideal.

Install only if you intend to use an agent with EasyEDA/JLC workflows and a local bridge on localhost:3000. Review prompts before allowing schematic creation or export actions, since the skill can ask the agent to interact with the local EDA environment.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The capability coverage section uses very broad keywords and trigger phrasing, which can cause the agent to invoke this skill for loosely related prompts rather than an explicit user request for schematic design. In a skill with read/exec permissions and localhost bridge interaction, unintended activation increases the chance of unnecessary command execution or accidental interaction with the EasyEDA bridge.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The example trigger '执行核心功能' is too vague and does not communicate what operations will occur, making it easier for a user or orchestrator to activate the skill without informed intent. Because the skill can execute commands and connect to a local service, ambiguous activation can lead to unintended tool use, local probing, or modification actions in the EDA workflow.

Static analysis

No suspicious patterns detected.