ClawHub
Back to skill

Security audit

SteamedClaw Chess

Security checks across malware telemetry and agentic risk

Overview

This skill is a local chess-position analyzer that runs a bundled JavaScript chess engine and shows no evidence of file mutation, credential use, network access, or persistence.

Install only if you are comfortable running a local JavaScript chess engine under Node.js. It should not need network access, credentials, or private files; use it with explicit FEN positions and keep search limits reasonable if CPU use matters.

SkillSpector

By NVIDIA
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)

Description-Behavior Mismatch

Medium
Confidence
93% confidence
Finding
The skill advertises chess position analysis, but this module exposes mutating game-management primitives such as move execution, AI play, piece placement/removal, and state export. That scope expansion increases the attack surface and can let downstream callers use the skill for capabilities not disclosed in the manifest, undermining least-privilege expectations and enabling unauthorized state manipulation in agent workflows.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.dynamic_code_execution

Dynamic code execution detected.

Critical
Code
suspicious.dynamic_code_execution
Location
chess-helper.js:727