ClawHub
Back to skill

Security audit

Vercel Composition Patterns

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only React guidance skill with one code-advice accuracy caveat, not evidence of malicious or hidden behavior.

This skill is reasonable to install for React composition guidance, but users should verify the React 19 API recommendations against their project's React version and official docs before applying them mechanically.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Intent-Code Divergence

Medium
Confidence
95% confidence
Finding
The guidance tells agents that React 19 `use()` replaces `useContext()` and suggests it may be used conditionally, which can cause code generation based on incorrect framework semantics. In an agent-focused skill, inaccurate API guidance is dangerous because it can systematically produce invalid, brittle, or misleading code across many refactors and implementations.

Static analysis

No suspicious patterns detected.