ClawHub
Back to skill

Security audit

Apple Search Ads

Security checks for vulnerabilities and agentic risk

Overview

This skill is purpose-aligned for Apple Search Ads management, but it should be reviewed because it handles live ad-account credentials and destructive ad operations without enough safety guidance.

Install only if you intend the agent to operate on a real Apple Search Ads account. Keep ASA credentials and token files protected, avoid exposing them in prompts or logs, and require explicit confirmation with exact resource IDs before any create, budget, status, or delete operation.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill instructs users to configure client credentials and describes local storage paths for config and token cache, but provides no warning that these values are sensitive secrets. In an agent environment, this can lead to accidental exposure in logs, shell history, screenshots, or overly permissive file storage, enabling unauthorized access to Apple Search Ads accounts.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill documents destructive `delete` operations for campaigns, ad groups, and keywords without any guidance to confirm user intent, preview targets, or warn about irreversible changes. In an agent setting, this increases the chance of accidental destructive actions from ambiguous prompts or mistaken IDs, especially because these commands affect live advertising resources.

Static analysis

No suspicious patterns detected.