ClawHub
Back to skill

Security audit

Epic Free Games

Security checks for vulnerabilities and agentic risk

Overview

This skill only teaches the agent how to fetch and format public Epic Games Store free-game listings, with no credential use, persistence, or local system changes.

Before installing, know that the skill will make unauthenticated network requests to Epic's public store API. If you want results in a specific language or region, tell the agent your preferred locale and country so it does not fall back to zh-CN/US.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The instructions say to default request parameters to zh-CN / US, which imposes a specific language choice when the user's locale is not known. This is a natural-language locale policy issue because the skill does not ask the user to choose a language or clearly justify why Chinese should be the default language.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.