ClawHub
Back to skill

Security audit

Supremacy 1914 War Cabinet

Security checks for vulnerabilities and agentic risk

Overview

The skill describes a game assistant that requires user approval for changes, with disclosed credentials and a separately downloaded server that remains unverified.

Review and pin the external server code before running it. Protect your game credentials and MCP token, keep access local or use HTTPS remotely, and leave writes disabled until you are ready to approve game actions. The server's enforcement of these controls was not verified.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 31)May include surrounding context.

cd supremacy1914-mcp/mcp_supremacy npm install npx playwright install chromium cp .env.example .env

optional login: S1914_USERNAME + S1914_PASSWORD (in-game name)

text

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 59)May include surrounding context.

Docker (HTTP on loopback)

bash
cp .env.production.example .env.production
# set S1914_MCP_TOKEN (openssl rand -hex 32)
# set login env if you want auto-login
npm run docker:up

MCP server referenced without pinned version: 'npx playwright'.

Medium
Category
MCP Rug Pull
Confidence
76% confidence
Finding

This is a conditional dependency supply-chain weakness, not evidence of malicious behavior: Playwright is a browser automation dependency, not the MCP server itself. If the preceding npm install does not provide a local Playwright executable, unversioned npx can fetch and execute a registry version that was not explicitly reviewed or pinned. A locally installed, lockfile-pinned dependency would substantially reduce this risk, but the supplied file does not establish that safeguard.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.