ClawHub
Back to skill

Security audit

ZenRows

Security checks across malware telemetry and agentic risk

Overview

The skill’s ZenRows functionality is coherent, but its setup guidance tells users or agents to run unverified remote installer scripts directly in a shell.

Review the installer source and prefer official, version-pinned, checksum- or signature-verified installation steps before using this skill. Do not let an agent automatically run the remote install commands; install and authenticate the `oo` CLI yourself, then use the skill only for the documented ZenRows connector actions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

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
98% confidence
Finding
The skill includes a curl-piped-to-shell installation command that executes a remote script directly from the network without integrity verification. If the remote host, CDN, TLS trust chain, or distribution path is compromised, users could execute arbitrary code on their machine, and placing this in a skill increases the chance an agent may surface or recommend it automatically during setup flows.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.