ClawHub
Back to skill

Security audit

Appstore Api

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed read-only App Store metadata API wrapper, with a documentation inconsistency about the reachable base URL but no evidence of hidden execution, mutation, persistence, or data theft.

Before installing, understand that the skill will send your ReplyNodes bearer key to the ReplyNodes gateway for read-only public App Store queries and consume prepaid credits. Store the key only in the agent secret store, do not paste it into chats, and treat the base-URL wording as inconsistent documentation to clarify with the publisher if your environment requires strict egress review.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Intent-Code Divergence

Medium
Confidence
96% confidence
Finding
The document contradicts itself by stating that no reachable host can be derived while repeatedly disclosing the concrete gateway `https://api.replynodes.com`. This is dangerous because downstream agents or users may rely on the false assurance to relax review, logging, or routing controls, and the inconsistency can conceal real external connectivity and data egress behavior.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.