Back to skill

Security audit

dota2 XG next game

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow Dota 2 schedule lookup that fetches public Liquipedia data, but it forces a Chinese/Beijing-time fan-commentary style with mocking language about Ame.

Install only if you want a Chinese-language XG schedule helper that uses Liquipedia via curl and reports times in Beijing time. Be aware it is intentionally written with fan-mocking language about Ame; users who want neutral, locale-aware match information should edit that style before using it.

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
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 (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill hard-codes a Chinese/Beijing-time output style and colloquial phrasing regardless of user preference, which can cause misleading scheduling information for users in other locales and reduce user control over language and formatting. In a scheduling skill, forced timezone conversion is especially risky because it can lead to users acting on incorrect match times.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill explicitly requires a derogatory persona toward a named individual and mandates taunting output such as insulting or mocking language. This creates abusive or harassing content on demand, undermines safe assistant behavior, and may target a real person with repeated hostile messaging.

Content

No source excerpt is available for this finding.