ClawHub
Back to skill

Security audit

Cuihua Monorepo Manager

Security checks for vulnerabilities and agentic risk

Overview

This skill is a low-risk monorepo helper, but its description overstates what the included script actually does.

Install only if you want a simple local workspace package lister, not a full monorepo automation system. Review expected behavior before relying on its advertised build optimization, versioning, or CI/CD claims.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Tp4

High
Category
MCP Tool Poisoning
Confidence
92% confidence
Finding
The description promises a broad monorepo management assistant with automation for orchestration, dependency management, and build optimization. The code only performs basic analysis of a monorepo by reading package.json files for configured workspaces and logging discovered package names. It does not modify dependencies, orchestrate tasks, optimize builds, or exhibit any AI-driven functionality. This is a materially narrower and different behavior than declared, so the description does not accurately represent the code.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The Quick Start section lists invocation examples like "Analyze monorepo dependencies" and "Optimize build order" without clarifying whether these are exact triggers, examples, or constrained to a specific tool context. Because the file provides no negative examples or activation boundaries, these phrases are broad enough to risk unintended invocation in ordinary project-management conversations.

Static analysis

No suspicious patterns detected.