ClawHub
Back to skill

Security audit

Dead Code Finder

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local dead-code reporting helper with some overstated capability claims but no hidden, persistent, networked, or destructive behavior in the inspected artifacts.

Installers should treat this as a read-only reporting aid, not a complete dead-code removal system. Review each finding before deleting code, especially in projects with dynamic imports, custom path aliases, barrels, or monorepos, because the scanner may miss references or report false positives.

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 Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
90% confidence
Finding

The code’s primary purpose is adjacent to the description but materially narrower. It is a dead-code reporting tool, not a dead-code removal tool. It detects only three categories: unused exports, unreferenced files, and unused dependencies. It does not analyze local dead functions or variables, and several advertised supports are absent or incomplete: tsconfig path aliases are parsed but never applied, monorepo-specific behavior is not implemented, and barrel export handling is not meaningfully present beyond simple regex matching. Dynamic imports are partially recognized, but overall the declared description overstates the actual capabilities.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.