ClawHub
Back to skill

Security audit

Gene Engine

Security checks across malware telemetry and agentic risk

Overview

Gene Engine mostly does what it says, but it needs review because it rewrites persistent agent-rule memory and one helper script can execute unintended local Python from crafted input text.

Install only if you are comfortable with a local heartbeat script changing persistent OpenClaw rule memory. Back up gene-state.json before recurring use, review state changes manually first, and avoid using gene-trigger.sh with untrusted or free-form text until its Python argument handling is patched.

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 (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill documentation clearly instructs execution of shell scripts and references reading and writing local state files, yet the metadata shown does not declare any permissions. That creates a transparency and consent problem: an agent or user may invoke the skill without understanding it can modify workspace files such as memory/gene-state.json and gene-metrics.log.

Missing User Warnings

Low
Confidence
83% confidence
Finding
The skill states that every run records metrics to a persistent local log file but does not warn the user about ongoing storage, retention, or possible inclusion of sensitive operational details. Even if the log is local, silent persistence can expose behavioral history, prompts, or outcomes to later readers and other tooling.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.