ClawHub
Back to skill

Security audit

app-store-connect-mcp

Security checks for vulnerabilities and agentic risk

Overview

This skill is a clearly disclosed App Store Connect connector, but users should treat it as sensitive because it can use App Store Connect credentials for account, tester, review, and financial workflows.

Install only if you intend to connect an agent to App Store Connect. Use the least-privileged API key that supports your intended workflows, avoid pasting the private key into unnecessary places, and require explicit user confirmation before actions such as inviting users, deleting testers, submitting builds, or responding to reviews.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger text is overly broad because it claims the skill should activate for virtually any request involving Apple developer, App Store Connect, or TestFlight management. In an agent environment, that can cause over-selection of this skill for loosely related prompts, increasing the chance of unnecessary access to sensitive account data or execution of write-capable actions such as inviting users, managing testers, or responding to reviews when a narrower skill would have been more appropriate.

Static analysis

No suspicious patterns detected.