ClawHub
Back to skill

Security audit

TextRazor

Security checks across malware telemetry and agentic risk

Overview

This TextRazor skill is not malicious, but it needs review because it presents itself as read-focused while exposing TextRazor management actions that can modify or delete resources.

Install only if you are comfortable giving the skill access through your OOMOL-connected TextRazor account. Before using classifier or dictionary manager actions, require explicit confirmation of the exact operation and target, especially for uploads, overwrites, and deletions. Prefer installing the oo CLI through a verified package or reviewed installer rather than piping a remote script directly into a shell.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Description-Behavior Mismatch

Medium
Confidence
96% confidence
Finding
The manifest markets the skill as for 'searching and reading data,' but the documented actions include management operations that can create, modify, or delete TextRazor resources. This mismatch can mislead an agent or user into invoking the skill under a read-only assumption, increasing the chance of unintended state changes.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger text says to use this skill for 'ANY TextRazor request,' which is overly broad and can cause the skill to be selected whenever TextRazor is mentioned, even when the user did not intend connector execution. In a tool-using agent, broad routing language increases the risk of accidental invocation of sensitive actions or unnecessary exposure of user data to the external 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
98% confidence
Finding
curl -fsSL https://cli.oomol.com/install.sh | bash

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.