ClawHub
Back to skill

Security audit

check-aox-info

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward AOX bridge information lookup with minor documentation and permission-scoping caveats.

Before installing, expect this skill to run a local Node script and contact the AOX public info API when invoked. It appears read-only and purpose-aligned, but users should be comfortable with the external network dependency and should only allow memory recording for non-sensitive public status results.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 4)May include surrounding context.

md
command: node script/index.js

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding

The skill declares command: node script/index.js, and the static analyzer detected network capability, but the manifest does not constrain allowed tools or permissions. That means the implementation may make outbound requests or use broader execution capabilities than users or reviewers can infer from the metadata, weakening least-privilege controls and increasing the blast radius if the script is compromised or behaves unexpectedly.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest description is written entirely in Chinese and presents the skill's purpose in a way that assumes Chinese-language use. There is no indication that users may interact in other languages or that the Chinese-only scope is an intentional, documented regional constraint.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · script/index.js (reported line 4)May include surrounding context.

js
#!/usr/bin/env node

const ENDPOINTS = {
  AOX: 'https://api.aox.xyz/info'
}

async function readInput() {

Static analysis

No suspicious patterns detected.