ClawHub
Back to skill

Security audit

Carbone

Security checks across malware telemetry and agentic risk

Overview

This Carbone skill is a disclosed OOMOL connector for listing, updating, and deleting Carbone templates, with no hidden code or malware telemetry detected.

Install only if you intend to let an agent use your OOMOL-connected Carbone account. Review any proposed update or delete payload carefully, and do not allow remote oo CLI installation unless you trust the OOMOL CLI source.

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
93% confidence
Finding
The skill description instructs the agent to use this skill for ANY Carbone request instead of calling the API directly, which is an overly broad routing rule. Broad trigger phrasing can cause over-selection of the skill in contexts it was not designed for, including write or destructive operations, increasing the chance of unsafe action execution or bypassing more appropriate specialized safeguards.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal