ClawHub
Back to skill

Security audit

Clawhub Publishing Mother Skill

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a publishing and promotion helper, but its public posting and tracking workflows are not clearly scoped for privacy or user confirmation.

Review this skill carefully before installing. Use it only with accounts and API tokens you are willing to let it use for public publishing or promotion, start with any available dry-run or preview mode, and confirm exactly what data it tracks, where it sends it, and how to disable monitoring or scheduled outreach.

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 (3)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill advertises impact tracking, community monitoring, and feedback collection but provides no notice about what data is collected, where it is sent, or whether user/community data is stored or profiled. In a publishing/community tool, this omission can lead to unintended collection of personal or behavioral data and creates privacy, consent, and compliance risk.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The workflow presents publish, promote, engage, and monitor commands as routine steps without warning that they may perform external network actions or create public-facing content. Users could trigger unintended publication, promotion, or scheduled outreach, causing data leakage, reputational harm, or accidental spam if run in the wrong context.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The quick-start section includes commands for publishing, promotion, tracking, reporting, and a full launch sequence that appear to trigger external actions, but it does not clearly warn users that these operations may create public artifacts, contact external platforms, or collect telemetry. In a publishing-oriented skill, users are especially likely to copy-paste commands from documentation, so the lack of explicit side-effect warnings increases the chance of unintended disclosure or unwanted external actions.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.