ClawHub
Back to skill

Security audit

Game Design Prototyping Companion

Security checks for vulnerabilities and agentic risk

Overview

This skill helps record game prototype decisions and can optionally render a local SVG map, with no evidence of hidden data access or unsafe persistence.

Install only if you want an agent to help maintain prototype logs and, when requested, create branch-map JSON and SVG files. Keep generated files in a project or output directory you control, and review the output path before allowing the renderer to run.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding
The skill instructs the agent to read reference files and run a script that writes an SVG output, which implies file read/write and code-execution-adjacent capabilities, but it does not declare any explicit tool scope or permissions boundaries. Without scoped permissions, an agent or runtime may grant broader filesystem access than necessary, increasing the risk of unintended file access, overwrites, or abuse if the skill is invoked with adversarial inputs or in a permissive environment.

Static analysis

No suspicious patterns detected.