ClawHub
Back to skill

Security audit

drama generator

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent script-to-video tool, but users should understand it installs external code and may send script or audio data to selected AI providers.

Install only if you trust the npm/GitHub source, preferably with a pinned version or in an isolated project. Use dedicated provider API keys, monitor usage costs, and avoid processing confidential, regulated, or copyrighted scripts unless the selected provider's data handling terms are acceptable.

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 README directs users to configure third-party TTS and speech-to-text providers and describes a pipeline where script text and audio are processed by OpenAI, Azure, Alibaba Cloud, or Tencent Cloud, but it does not clearly disclose that user-provided content will be transmitted off-device. This is a real transparency and privacy issue because users may assume the tool is fully local except for API-backed synthesis, and may unknowingly submit sensitive scripts or voice content to external services.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The documentation instructs users to provide scripts and use external TTS/Whisper services, but it does not clearly warn that script text and derived audio may be transmitted to third-party providers and that generated media is written to local disk. This can cause unintentional disclosure of sensitive or copyrighted content, especially if users assume processing is fully local.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.