ClawHub
Back to skill

Security audit

MTG Wiki (English)

Security checks for vulnerabilities and agentic risk

Overview

This MTG reference skill is coherent and disclosed; its main caution is that card lookups may contact third-party MTG APIs.

Install only if you are comfortable with MTG lookup terms being sent to mtgch or Scryfall when API-backed searches are used. Review the linked GitHub repository before cloning it or running its Python scripts for the full local database.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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)

External Transmission

Medium
Category
Data Exfiltration
Content
API priority:
1. mtgch API (`https://mtgch.com/api/v1/`) — Chinese first, bilingual
2. Scryfall API (`https://api.scryfall.com/`) — English primary
3. Local 37k Oracle DB — offline exact match

## Layer System Quick Reference (CR 613)
Confidence
88% confidence
Finding
The skill explicitly prioritizes remote APIs (mtgch and Scryfall) for card data, which causes user queries and possibly card names or derived prompts to be transmitted to third-party services. Even though the purpose is legitimate, external transmission can leak user activity, create privacy concerns, and introduce supply-chain trust in unverified remote content. The context makes this somewhat less dangerous because the transmitted data is mostly game-related, but it still crosses a trust boundary.

Static analysis

No suspicious patterns detected.