ClawHub
Back to skill

Security audit

CRUD Code Generator

Security checks across malware telemetry and agentic risk

Overview

This is a coherent CRUD code-generation skill, but it can write many project files and run build commands, so users should review its output carefully.

Install only if you want an agent to inspect a Java/Vue project, generate source and SQL files, and run local build validation. Use it in a version-controlled project, confirm the project roots first, review generated diffs and SQL before applying them, and avoid running Maven or npm validation in untrusted repositories.

SkillSpector

By NVIDIA
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 (4)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger phrases are very broad and can activate on generic requests like generating interfaces or CRUD from table definitions, increasing the chance the skill runs outside the user's precise intent. In a skill that can scan project structure, generate files, and optionally run validation commands, unintended invocation can lead to unreviewed filesystem modifications or command execution in the wrong repository context.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The README advertises automatic project scanning, code and SQL generation, and build/dev validation, but does not warn that these actions may modify the filesystem or invoke commands. In an agent context, this omission is dangerous because users may not realize the skill could inspect repositories, write multiple files, and execute tools like Maven or npm, creating integrity, safety, and operational risks.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill explicitly instructs creating many backend, frontend, and SQL files, but it does not require a clear user-facing warning or explicit confirmation that the agent will modify the user's repository and filesystem. In an agent setting, silent or insufficiently disclosed write actions can lead to unintended codebase changes, accidental overwrites, and persistence of generated artifacts the user did not expect.

Missing User Warnings

Low
Confidence
87% confidence
Finding
The skill directs execution of `mvn clean package` and may run `npm run dev`, but it does not clearly warn that these commands execute in the user's project environment and may trigger builds, plugins, network access, or long-running processes. Even common build commands can have side effects in untrusted or unfamiliar repositories, especially when Maven or npm hooks are present.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.