ClawHub
Back to skill

Security audit

clawhub

Security checks across malware telemetry and agentic risk

Overview

This looks like a normal local toolkit for creating skills, but its listing declares unrelated crypto and purchase capabilities that do not fit the files.

Install only if you intend to use a local skill-building toolkit. Run the bundled scripts in a dedicated workspace, review generated files before packaging or sharing them, and verify why the listing claims crypto and purchase capabilities even though the artifacts do not use them.

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 (1)

Vague Triggers

Medium
Confidence
78% confidence
Finding
The description is broad enough to trigger on many generic requests about creating or updating skills, causing the agent to load guidance that includes file modification, script execution, and packaging behavior. Over-broad triggering increases the chance of the skill activating in contexts where those actions are unnecessary or unsafe, expanding the attack surface for prompt-induced misuse.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.