ClawHub
Back to skill

Security audit

Clawdhub

Security checks across malware telemetry and agentic risk

Overview

This skill is a legitimate ClawdHub CLI helper, but it exposes broad install, update, login, and publish actions without enough guardrails for agent use.

Install only if you want an agent to manage ClawdHub skills from your machine. Require explicit approval before running global npm install, login, publish, `update --all`, `--force`, or `--no-input`; verify the registry URL, target directory, package provenance, and files being published first.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
89% confidence
Finding
The skill directly documents install, update, and publish commands that modify the local filesystem and can update one or all installed skills, including force and no-input modes, but it does not warn the user about these side effects. In an agent-skill context, omission of this warning is dangerous because it increases the chance of unintended bulk changes, silent overwrites, or supply-chain updates being performed without informed user consent.

Missing User Warnings

Medium
Confidence
86% confidence
Finding
The documentation instructs users to authenticate and identifies a default remote registry, but it does not warn that login may transmit credentials and that search/install/publish operations send metadata or skill contents over the network. In this context, publish is especially sensitive because local skill files may be uploaded to an external service, creating privacy, credential-handling, and data-exfiltration risks if users are not clearly informed.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.