ClawHub
Back to skill

Security audit

Axiomata Guard Scanner

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a security-audit helper for OpenClaw skills, with no evidence of hidden actions or harmful behavior.

Install only if you want this skill to be available broadly for OpenClaw skill security reviews. Be aware it may be selected for general skill-installation or audit requests, so keep final install decisions user-directed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger text is very broad: 'Before installing any skill' and 'any security audit of OpenClaw skills' can cause this skill to be invoked in many contexts, including routine workflows where it may be unnecessary. Overly broad invocation criteria can lead to prompt/skill hijacking, denial of workflow efficiency, or accidental precedence over more specific skills, especially because this skill positions itself as a universal scanner for any agent.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.