ClawHub
Back to skill

Security audit

ClawHub Publish Official

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward ClawHub CLI helper skill, with disclosed commands for searching, installing, updating, logging in, and publishing skills.

Install this only if you intend to use the ClawHub CLI. Verify the npm package provenance, avoid bulk forced updates unless you understand the impact, and review skill directories for secrets or private files before publishing.

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
88% confidence
Finding
The skill includes forceful, non-interactive update examples such as `clawhub update --all --no-input --force` without any warning that they may overwrite installed skills or apply changes without review. In an agent context, this increases the chance of unattended bulk modification of the local environment and makes accidental or unsafe upgrades more likely.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The authentication and publishing sections instruct the user to log in and publish a skill to an external marketplace but do not disclose that skill contents, metadata, and account-linked information may be transmitted to `clawhub.com`. This can lead to unintended data exposure, especially if users publish from directories containing sensitive or unreviewed files.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal