ClawHub
Back to skill

Security audit

Video Intent Studio

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent Volcengine Ark video-generation helper, with expected network and API-key use that users should understand before generating.

Install only if you intend to generate videos through Volcengine Ark. Review the final prompt before confirming, avoid including secrets or sensitive personal or business data, use a dedicated Ark API key, and leave ARK_VIDEO_TASKS_URL unset unless you trust the alternate endpoint.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill instructs the agent to execute local Python scripts, read API credentials from environment variables, and make outbound network requests, but it declares no permissions. This creates a capability/permission mismatch: reviewers and runtime policy may not realize the skill can access secrets and external services, which increases the risk of unauthorized data exfiltration, unintended API usage, or unsafe execution if the skill is invoked in a broader context.

Context-Inappropriate Capability

Medium
Confidence
86% confidence
Finding
The script expands credential sourcing beyond explicit CLI arguments and environment variables by reading API keys from the Windows registry. That broader secret discovery behavior is not necessary for a simple video-generation helper and can cause the tool to use sensitive credentials the user did not intend to expose to this workflow, increasing the blast radius if the script or its configuration is abused.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The guide explicitly instructs users to send prompts through a bundled HTTP generation script and to set a cloud API key, but it provides no warning that prompts and possibly sensitive creative or personal content will be transmitted to a third-party service. In a multi-turn workflow tool, users may reasonably include confidential project details, so the lack of disclosure and data-handling guidance creates a real privacy and compliance risk.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.