ClawHub
Back to skill

Security audit

D&D 5e Toolkit

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward D&D utility skill that runs a user-invoked Python script and contacts the disclosed public D&D 5e API for game data.

Installing this skill means allowing a local Python script to run when invoked and to contact the D&D 5e API for lookup data. Avoid using private campaign details as lookup terms if you do not want those request paths or queries associated with that external service.

SkillSpector

By NVIDIA
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
91% confidence
Finding
The skill documentation states it uses the official D&D 5e API, which implies outbound network access, but the skill metadata declares no corresponding permissions. This is a real security and governance issue because undeclared network capability reduces transparency, prevents proper review of data flows, and could allow unexpected external communication if the implementation changes or is compromised.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.