ClawHub
Back to skill

Security audit

MotherDuck

Security checks across malware telemetry and agentic risk

Overview

This MotherDuck connector is coherent and disclosed, but it gives an agent broad account-administration and token-management power that users should review carefully before installing.

Install only if you trust OOMOL and want this agent to administer your MotherDuck organization through the oo CLI. Treat token listing, token creation, user deletion, and configuration changes as privileged actions; require explicit confirmation for any write or destructive operation, and avoid using it in conversations that include untrusted instructions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The description says to use this skill for "ANY MotherDuck request" and "instead of calling the API directly," which is an overly broad invocation trigger. This can cause the agent to route a wide range of requests, including sensitive or destructive ones, into a high-privilege connector without sufficient narrowing or contextual safeguards.

Credential Access

High
Category
Privilege Escalation
Content
- `delete_user` — Permanently delete a MotherDuck user and all of their data. [destructive]
- `get_user_duckling_config` — Retrieve MotherDuck Duckling configuration for a user.
- `list_active_accounts` — List active MotherDuck accounts and their active Ducklings in the organization.
- `list_tokens` — List MotherDuck access tokens for a user.
- `set_user_duckling_config` — Set MotherDuck Duckling configuration for a user. [write]

## Safety
Confidence
88% confidence
Finding
access tokens

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal