Back to skill

Security audit

World Cup Content Generator

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-only World Cup content-writing skill with no code execution, credential access, persistence, or hidden side effects.

Before installing, understand that this skill will shape an assistant into a World Cup content editor. Users should provide real match facts and review outputs for accuracy before publishing, especially scores, injuries, lineups, sponsorship disclosures, and any prediction-game wording.

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)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 92)May include surrounding context.

md
- Works as a `SKILL.md` for Claude / Codex / Cursor / any SKILL.md-compatible agent; the same text can be pasted into a custom GPT / agent builder as the system

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The style section explicitly requires content to be written in English. Under the policy for natural-language violations, forcing a specific language is a finding unless the skill offers opt-in choice or clearly documents a justified region-specific constraint, which this file does not.

Content

No source excerpt is available for this finding.