Back to skill

Security audit

civ6lib

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local Civilization 6 rules helper with a documented accuracy bug but no evidence of hidden access, persistence, credential use, or unsafe execution.

Safe to install from a security perspective for Civ6 planning or rules-reference use, but do not treat canal placement validation as authoritative until the flat-land check is fixed and tested.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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
Findings (1)

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

This is a true logic flaw: the Canal validation routine documents that canals must be built on flat land, but no code checks tile.is_flat_land or equivalent for DistrictType.CANAL. In a rules engine library, this can cause downstream agents or applications to accept illegal game states, producing incorrect planning, validation, or automation results.

Content

No source excerpt is available for this finding.