ClawHub
Back to skill

Security audit

Vercel Zero Explorer

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only skill for learning Vercel Zero, with clear safety boundaries and no packaged code or persistence.

Before installing, treat this as reference material only: run any Zero commands yourself in an isolated disposable workspace, avoid production or sensitive data, and verify command syntax against official Zero docs because the language is experimental and changes quickly.

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)

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill repeatedly states it does not execute commands, read files, or interact with the user environment, but Example 3 describes a workflow that says to 'Execute and capture JSON diagnostics' and implies autonomous re-execution. That inconsistency can mislead an agent into crossing the declared execution boundary, especially in tool-using environments where examples are often treated as operational guidance rather than illustrative prose.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The trigger section explicitly defines activation examples only in Chinese and English and requires users to "must name Vercel Zero explicitly" in those listed forms. This creates a locale/language constraint in the skill's natural-language routing behavior without clearly offering equivalent support for other languages or stating that language choice is user-selectable.

Content

No source excerpt is available for this finding.