ClawHub
Back to skill

Security audit

Apple Ads CLI

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Apple Search Ads reporting helper that needs Apple Ads credentials but does not show hidden, destructive, or unrelated behavior.

Install only if you intend to use Apple Search Ads reporting. Verify the npm package before global installation, use the least-privileged Apple Ads access available, keep tokens and private keys out of chat/logs, and treat generated reports as sensitive business data.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger phrase "search ads" is overly generic and can match many unrelated advertising requests, causing the skill to activate outside its intended Apple Search Ads scope. Over-broad invocation increases the chance an agent will use this skill in the wrong context, exposing Apple Ads account metadata or prompting unnecessary credential handling.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill instructs use of OAuth access tokens and local credential files but does not explicitly warn against exposing, echoing, logging, or requesting secret material in chat. In an agent setting, that omission can lead to unsafe handling of tokens or credential paths, increasing the risk of credential disclosure or misuse.

Static analysis

No suspicious patterns detected.