ClawHub
Back to skill

Security audit

Personal Assistant

Security checks across malware telemetry and agentic risk

Overview

This appears to be a real OpenMarlin integration, but it handles billing and persistent API keys with enough credential and provenance risk that users should review it before installing.

Install only if you intend to use OpenMarlin and trust the publisher/source. Verify the configured OPENMARLIN_SERVER_URL before registration, require explicit approval for remote executions, video tasks, top-ups, referral lookups, and checkout flows, and rotate any API key that may have been printed or captured in logs.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
94% confidence
Finding
The skill describes and instructs use of broad capabilities including environment access, file read/write, network access, shell execution, and MCP interactions, but does not declare permissions. That mismatch weakens the platform's trust and review model because users and enforcement layers may not understand the true operational scope before activation, increasing the chance of over-privileged execution and unsafe side effects.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The code prints the issued API key secret directly to stdout and even emits a ready-to-copy export command. In CLI and agent environments, stdout is often logged, captured in transcripts, terminal history, CI artifacts, or telemetry, which can expose a long-lived credential and enable unauthorized access to the OpenMarlin/OpenClaw workspace.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.