ClawHub
Back to skill

Security audit

Kernel

Security checks across malware telemetry and agentic risk

Overview

This appears to be a disclosed Kernel integration whose broad trigger needs caution but does not show hidden or malicious behavior.

Install this only if you want the agent to manage Kernel browser/API resources. Before using it for write or delete operations, confirm the exact resource and action, and prefer a least-privilege Kernel API key where possible.

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

High
Confidence
95% confidence
Finding
The manifest description instructs the agent to use this skill for "ANY Kernel request" and to prefer it over calling the API directly, which is an overly broad trigger that can cause the skill to be invoked for a wide range of read, write, and destructive operations without sufficient task-specific gating. In context, the skill exposes state-changing and destructive actions, so broad auto-selection increases the chance of unintended data modification or deletion if the agent routes requests here too aggressively.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.