ClawHub

Ai Animation Free

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed cloud video-animation connector, not local-only software, and its sensitive behavior is mostly expected for that purpose.

Install only if you are comfortable sending selected images, videos, audio, URLs, prompts, and session state to NemoVideo for processing. Treat NEMO_TOKEN as sensitive, check credit/export limits before relying on it, and avoid uploading confidential media.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Description-Behavior Mismatch

Medium
Confidence
91% confidence
Finding
The skill markets itself as a simple image/text-to-animation tool, but the body defines a much broader remote editing system with uploads, state inspection, credits checks, timeline manipulation, and export orchestration. This creates a scope-transparency problem: users may provide files and prompts under a narrower trust assumption than the actual remote capabilities and data flows warrant.

Vague Triggers

Medium
Confidence
88% confidence
Finding
Routing 'Everything else' to the SSE generation action is an overly broad trigger that can capture unrelated user input and send it to the remote backend. This increases the chance of unintended data exfiltration, surprising tool activation, and actions outside the user's expected intent.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill documentation does not clearly warn users that uploaded files, prompts, and session data are transmitted to a third-party cloud backend. This is dangerous because users may unknowingly share sensitive media, text, or metadata with an external service under a mistaken assumption of local-only processing.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal