ClawHub
Back to skill

Security audit

BYOCB ArbInjectionSkill

Security checks across malware telemetry and agentic risk

Overview

This skill has a real security-monitoring purpose, but it asks for persistent background monitoring, external alerts, and unpinned daily self-updates without enough user control.

Install only if you trust and have reviewed the linked repository. Prefer pinning a specific commit or release, disabling the daily auto-update schedule, running the monitor in an isolated environment, limiting API keys, and explicitly confirming when background monitoring and third-party alerts are allowed.

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
89% confidence
Finding
The skill explicitly states it runs automatically in the background and should notify users when findings occur, but it does not define clear activation, consent, scope, or termination boundaries for that autonomous behavior. In an agent setting, this can cause unintended continuous monitoring and outbound messaging, increasing the risk of surprise actions, privacy issues, resource abuse, or alerts being sent without an explicitly scoped user request.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.