ClawHub
Back to skill

Security audit

BYOCB ArbInjectionSkill

Security checks across malware telemetry and agentic risk

Overview

This skill has a legitimate security-monitoring purpose, but it asks users to run and automatically update unpinned external code in a persistent background monitor.

Review before installing. Pin the external repository to a specific audited commit, inspect dependencies before npm install, avoid automatic daily git pull/npm install, explicitly approve any alert channel, and use scoped API keys only if you accept that scan context may leave your environment.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Low
Confidence
87% confidence
Finding
The skill explicitly states that findings are saved to `./results/`, but it does not clearly warn users in the install/runtime guidance that continuous background monitoring will persistently write potentially sensitive scan artifacts to local disk. In a long-running monitor, this can lead to unnoticed accumulation of data, local information exposure, or disk usage issues, especially if users assume the tool is only performing transient analysis.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.