ClawHub

Clerk

Security checks across malware telemetry and agentic risk

Overview

This Clerk administration skill is coherent, but it grants sensitive account-management power with activation and confirmation rules that are too broad for identity operations.

Install only if you intentionally want an agent to administer Clerk through OOMOL. Before any create, update, delete, lock, unlock, ban, or unban operation, verify the requester is authorized, confirm the exact user ID and payload, and keep audit records for identity/security changes.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger language is excessively broad and can cause the skill to activate for almost any Clerk-related mention, including casual discussion or analysis that does not require tool use. In a security/identity context with create, update, lock, ban, and delete capabilities, this increases the chance of unintended invocation and over-privileged action selection.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill exposes an account-unlock operation with no warning, authorization guidance, or confirmation requirements, even though unlocking a user changes account security state. In an agent setting, this increases the chance of unauthorized or insufficiently verified account recovery actions, especially if the model executes the action from ambiguous or malicious prompts.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal