ClawHub
Back to skill

Security audit

Lowcode Platform Development

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward project scaffolding helper, but users should confirm dependency installs and build steps before running it.

Before installing or using this skill, verify or supply the missing generate_project.ps1 and real templates yourself, choose a target directory, and approve the npm and Maven commands because they may download dependencies and run package build hooks.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill instructs execution of a local PowerShell scaffold script that writes files and runs dependency/build commands (`npm install` and `mvn package`) without an explicit user-facing warning about those side effects. This is dangerous because build/install steps can execute package lifecycle hooks, modify the filesystem extensively, and consume network/resources, increasing the chance of unintended code execution or environment changes when triggered implicitly.

Static analysis

No suspicious patterns detected.