ClawHub
Back to skill

Security audit

Mistral AI

Security checks across malware telemetry and agentic risk

Overview

This skill is mostly coherent for managing Mistral AI through OOMOL, but it includes high-impact Mistral actions and unsafe first-time installer commands that deserve manual review.

Install only if you intend to let an agent operate your Mistral AI account through OOMOL. Review every write, upload, sharing, or delete request before approving it, and install the `oo` CLI manually from trusted documentation with verification rather than letting the skill run pipe-to-shell installer commands.

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 trigger text says to use this skill for ANY Mistral AI request and instead of calling the API directly, which is overly broad and can cause the agent to invoke a high-privilege skill in situations where a narrower or safer path would be preferable. Because the skill exposes read, write, and destructive operations, broad routing increases the chance of unintended state-changing actions being selected or prepared from ambiguous user prompts.

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

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.