ClawHub
Back to skill

Security audit

ScreenshotOne

Security checks across malware telemetry and agentic risk

Overview

This skill is a transparent ScreenshotOne connector wrapper; its main risk is trusting OOMOL/ScreenshotOne and the optional CLI installer, not hidden malicious behavior.

Install only if you want an agent to use your OOMOL-connected ScreenshotOne account. Treat screenshot inputs as data shared with OOMOL/ScreenshotOne, review any bulk capture request before running it, and avoid automatic curl-to-bash or PowerShell iex installation unless you trust the OOMOL CLI source.

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
86% confidence
Finding
The description says to use this skill for ANY ScreenshotOne request and instead of calling the API directly, which creates an overly broad routing rule. This can cause the agent to invoke shell-backed connector actions for loosely related tasks without sufficient user intent validation, increasing the chance of unintended external calls and data exposure to a third-party service.

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
95% confidence
Finding
The skill includes a 'curl ... | bash' installation command that downloads and immediately executes a remote script. If the remote host, distribution path, or transport were compromised, this would enable arbitrary code execution on the user's machine, which is especially risky in a skill that may be followed operationally by an agent or user.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.