Back to skill

Security audit

Gameinformer News

Security checks for vulnerabilities and agentic risk

Overview

This skill only helps fetch and format public Game Informer RSS headlines, with minor routing and language-preference caveats.

Installers should know this skill may answer broad gaming-news prompts with Game Informer results and may respond in English even if another language is preferred. It otherwise appears limited to public feed retrieval and headline formatting.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The trigger substrings include broad terms like "game news" and references to "game informer," which can cause the skill to activate for generic gaming-news requests rather than only site-specific requests. This can misroute user intent, override more appropriate skills, and increase the chance of unintended external fetches to this source.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill mandates English output regardless of the user's language preference, which can override user intent and platform localization expectations. While not a classic security flaw, it is a policy and safety issue because it can degrade trustworthy behavior and cause the agent to ignore higher-priority user needs.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

Repeating the English-only requirement as a non-negotiable rule reinforces behavior that may conflict with user instructions or system language policies. The repetition makes the constraint more likely to dominate at runtime, increasing the chance the agent ignores legitimate user preferences.

Content

No source excerpt is available for this finding.