ClawHub

Anthropic

Security checks across malware telemetry and agentic risk

Overview

This Anthropic connector is mostly coherent, but it asks agents to use a connected third-party account for any Anthropic-related request and includes an unverified remote installer.

Install only if you intend your agent to use OOMOL as the intermediary for Anthropic API actions. Treat general Anthropic questions as out of scope unless you actually want an account-backed API call, review message payloads before create_message, and prefer a verified or manually inspected oo CLI installation path over piping a remote script directly into the shell.

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
82% confidence
Finding
The trigger scope is overly broad, directing agents to use this skill for 'ANY Anthropic request' and 'Whenever a task involves Anthropic.' That can cause unnecessary or unintended invocation for loosely related prompts, increasing the chance of external tool use, data disclosure to a third-party service, or actions being taken when simple discussion or local reasoning would suffice.

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

VirusTotal findings are pending for this skill version.

View on VirusTotal