ClawHub

Test

Security checks across malware telemetry and agentic risk

Overview

This skill appears legitimate for GA4/GTM automation, but it routes users to external tooling with Google OAuth access that can change or publish GTM containers.

Install only if you trust the external analytics-tracking tooling it pulls in. Use a limited Google/GTM account, verify OAuth scopes, keep artifact directories private, strip sensitive URL/referrer data before collection where possible, and delete or revoke `credentials.json` when finished.

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 guidance instructs implementers to attach full `page_location` and `page_referrer` values to every event, but provides no warning that URLs and referrers can contain sensitive data such as query parameters, reset tokens, email addresses, internal paths, or third-party identifiers. In an analytics automation skill, this omission is practically actionable and can lead to systematic over-collection of personal or confidential data across all tracked events.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The documentation explicitly specifies storing a reusable Google OAuth token cache in `credentials.json` inside the artifact directory, but provides only a brief 'never commit this file' note and no stronger handling guidance such as encryption, restrictive permissions, exclusion from snapshots/backups, or safe cleanup. Because this skill is designed to generate many workflow artifacts in a shared output tree, users may inadvertently expose valid tokens through local backups, artifact sharing, or poor filesystem hygiene.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal