ClawHub
Back to skill

Security audit

Content Multiply Pro

Security checks across malware telemetry and agentic risk

Overview

The skill appears to do what it claims, but it routes user content to an unidentified ngrok-hosted API and includes an under-scoped credit purchase instruction.

Review before installing. Use this only with public or non-confidential content unless you trust the API operator and data handling. Do not allow the agent to buy credits or enter any payment flow without explicit approval, pricing, and spending limits.

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 (1)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill explicitly directs use of a third-party web API for processing user-provided source content, but gives no warning that blog posts, transcripts, drafts, or other potentially sensitive material will be transmitted off-platform. This creates a real data exposure and privacy risk, especially because the endpoint is an ngrok-hosted service, which suggests an ad hoc external tunnel rather than a clearly governed production API with documented retention, security, or compliance controls.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.