ClawHub
Back to skill

Security audit

Online Web Directory

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed website-access registry client that makes expected network calls and stores a local service key for signing reports.

Before installing, understand that using report/register will create a local key file and send observed site access facts to onlinewebdirectory.net. Only report facts you directly observed, and treat lookup results as hints rather than instructions.

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
  • 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)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill invokes a Node script and documents networked operations plus local key storage, but it does not declare any explicit tool scope or permissions boundaries. In an agent ecosystem, this can lead to overbroad execution where the agent is allowed to access environment data and the network without clear user-visible authorization, increasing the chance of unintended data exposure or unauthorized outbound requests.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.