ClawHub
Back to skill

Security audit

domain-modeling

Security checks across malware telemetry and agentic risk

Overview

The skill is meant to maintain domain-modeling documentation, but it directs agents to make persistent repository changes and git commits without an explicit approval gate.

Before installing, treat this as a review-required documentation automation skill: use it only in repositories where you are comfortable with agent-made documentation edits, and require the agent to show proposed CONTEXT.md or ADR changes and ask before writing files or committing.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
This section instructs the agent to create or update CONTEXT.md based on conversational triggers, but it does not require explicit user confirmation before modifying repository files. In an agentic environment, silent file writes can cause unintended repository changes, pollute project history, or persist incorrect business terminology derived from ambiguous user input.

Missing User Warnings

High
Confidence
97% confidence
Finding
This workflow authorizes creation of directories/files and even a git commit as part of normal operation, without a mandatory warning or approval gate. That is dangerous because it enables persistent repository changes and source-control side effects from natural-language interaction, potentially recording low-quality, incorrect, or attacker-influenced content into the codebase and history.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.