ClawHub

urlscan.io

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed urlscan.io connector wrapper with expected credential and write-action behavior, though users should be cautious with the optional CLI install command.

Install only if you are comfortable connecting an OOMOL account to urlscan.io and allowing the agent to run oo connector commands. Review the CLI install script or use an official installer path before running the pipe-to-shell setup, and confirm submit_scan payloads because submitted URLs may be sent to urlscan.io and change account/service state.

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
94% confidence
Finding
The description says to use this skill for "ANY urlscan.io request" and "Whenever a task involves urlscan.io, use this skill," which is a very broad activation condition. It does not provide boundaries or negative examples clarifying when the skill should not be invoked, increasing the chance of accidental triggering from general discussion of urlscan.io.

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

64/64 vendors flagged this skill as clean.

View on VirusTotal