ClawHub
Back to skill

Security audit

apple-search-adser

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Apple Search Ads consulting skill with no executable code, persistence, credential handling, or external data transfer.

Installers should understand this skill gives tactical advertising budget and campaign-optimization advice, but it does not connect to Apple Search Ads, change campaigns, read credentials, or run code. Review recommendations before applying them in an ad account because they can affect spend.

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
  • 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 (3)

Context Leakage

High
Category
Data Exfiltration
Content
1. Extract what the user already told you (don't re-ask)
2. Summarize your diagnosis, propose a focus area, give a preview — then wait for confirmation

## Step 1: Extract Context

From the user's message, extract:
- App name and category
Confidence
75% confidence
Finding
Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The activation guidance says to use the skill for broad phrases such as "my CPA is too high," "my ads aren't converting," and "scaling app installs," which are common across many ad platforms and not specific to Apple Search Ads. Without clearer constraints or exclusion examples, this could cause unintended invocation for generic advertising questions.

Natural-Language Policy Violations

Medium
Confidence
93% confidence
Finding
This JSON file contains natural-language prompts and expected outputs entirely in Chinese, indicating the skill is designed to operate in a single language. Because there is no visible opt-in, alternative language support, or documented region-specific justification in this file, it presents a language/locale policy concern under the stated rules.

Static analysis

No suspicious patterns detected.