ClawHub
Back to skill

Security audit

Court Prep

Security checks across malware telemetry and agentic risk

Overview

This court-prep skill mostly does what it says, but it includes an under-disclosed local notes/history tool that can retain sensitive case details.

Review before installing. The court-prep generator itself appears locally run and purpose-aligned, but avoid entering sensitive names, facts, identifiers, or case strategy into the add/search/run helper unless you are comfortable with that data being stored in local log files. Do not rely on the remove command to erase previously stored entries.

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
83% confidence
Finding
The skill description and trigger text are broad enough that an agent may activate this skill in situations that only loosely relate to legal or court topics. In a legal-assistance context, unintended activation is risky because it can surface procedural guidance or task automation inappropriately, potentially causing users to rely on the wrong workflow or receive legal-process advice without clear scoping.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The script persistently logs command arguments to history.log and stores user-provided content in data.log without notifying the user or obtaining consent. This can expose sensitive information typed as arguments, such as names, case details, identifiers, or other confidential material, especially since commands like add, search, and run pass raw arguments into logs.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.