ClawHub
Back to skill

Security audit

Rentman

Security checks across malware telemetry and agentic risk

Overview

This skill is a read-oriented Rentman connector guide that is coherent and does not show hidden, destructive, or exfiltrating behavior.

Install only if you want Codex to read Rentman data through your connected OOMOL account. Be aware that first-time setup may ask you to install and sign into the oo CLI, and you should require explicit confirmation before allowing any future Rentman action that would create, update, delete, or overwrite data.

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 manifest description says to use this skill for ANY Rentman request and instead of calling the API directly, which creates an overly broad routing trigger. This can cause the agent to invoke the skill for unrelated or higher-risk Rentman tasks without adequate scoping, increasing the chance of unintended connector use and bypassing more task-specific safety checks.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.