ClawHub
Back to skill

Security audit

Art Process Video

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed WeryAI art-video generation helper that uses an API key and paid network calls, with no evidence of hidden or destructive behavior.

Install only if you trust the skill with your WeryAI account usage. Keep WERYAI_API_KEY secret and rotatable, confirm URL override environment variables are unset or trusted, and review each confirmation table because successful runs can consume paid WeryAI credits.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The implicit trigger phrase is broad enough to match ordinary art-related user requests without a clear requirement that the user intended to invoke this specific skill. That can cause unintended skill activation, routing prompts into a video-generation workflow when the user may only be describing an art process, which increases the chance of incorrect tool use and policy bypass around capability boundaries.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.env_credential_access

Environment variable access combined with network send.

Critical
Code
suspicious.env_credential_access
Location
scripts/video_gen.js:68