FFHub

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed FFHub connector helper, with no artifact-backed evidence of hidden data theft, destructive behavior, or deceptive execution.

Install this only if you intend to let your agent operate FFHub through OOMOL. Review any create task payload before approval, and consider installing the `oo` CLI through a verified guide or package manager rather than piping a remote installer directly into your shell.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
Findings (2)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The skill is scoped to be used for 'ANY FFHub request,' which is an overly broad activation condition that can cause the agent to invoke this skill in situations where a narrower, task-specific tool selection policy would be safer. Overbroad routing increases the chance of unintended state-changing operations or unnecessary exposure to the connector's capabilities, especially because this skill includes create/update behavior in addition to read-only actions.

External Script Fetching

High
Category
Supply Chain
Content
- **`oo: command not found`** — install the oo CLI (other platforms: <https://cli.oomol.com/install-guide.md>):

  ```bash
  curl -fsSL https://cli.oomol.com/install.sh | bash    # macOS / Linux
  ```

  ```powershell
Confidence
97% confidence
Finding
curl -fsSL https://cli.oomol.com/install.sh | bash

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal