ClawHub
Back to skill

Security audit

elsewhen

Security checks for vulnerabilities and agentic risk

Overview

This is a clearly documented game skill that uses a third-party server and user-provided model key, with the main risks disclosed up front.

Use this only if you are comfortable with a Traditional Chinese-only game and with sending a dedicated, low-limit OpenRouter or Google AI Studio key to Elsewhen's server. Keep the Elsewhen token private because it can access saves and the stored key for this service.

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
96% confidence
Finding

The documentation states 'Chinese only' and that the world answers in Chinese regardless of the language the user writes in. This is a natural-language locale restriction presented as mandatory behavior, without offering a language choice or opt-in within the skill itself.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.