ClawHub

AgentQL

Security checks across malware telemetry and agentic risk

Overview

The AgentQL integration is mostly coherent, but it needs review because its setup path can run a remote installer script without an explicit approval gate.

Install the oo CLI only if you trust OOMOL and preferably after reviewing the official installer yourself. Confirm any create_browser_session or other state-changing AgentQL action before it runs, and be aware that AgentQL queries, target webpages, session metadata, usage data, and connected account credentials are handled through OOMOL/AgentQL services.

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
95% confidence
Finding
The description says to use this skill for "ANY AgentQL request" and "Whenever a task involves AgentQL," which is a very broad trigger without explicit boundaries or negative examples. In a markdown/manifest context, this can overlap with many ordinary tasks that merely mention AgentQL, making activation conditions insufficiently specific.

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
90% confidence
Finding
curl -fsSL https://cli.oomol.com/install.sh | bash

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal