ClawHub
Back to skill

Security audit

AI Animation Studio

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed AI animation workflow that uses local media tools and a Doubao-backed helper, with privacy and setup considerations but no evidence of hidden or destructive behavior.

Install only if you are comfortable using Doubao/Volcengine-backed media generation, possible API quota or cost usage, and sending story prompts or image references to that provider. Verify the hardcoded doubao-media path points to a trusted local skill and keep the D:\AI视频资源 folder limited to media assets you intend the workflow to use.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger phrases are very broad and map closely to ordinary user requests about animation creation, which increases the chance the skill is invoked when a user did not specifically intend to use it. Because this skill can drive external media-generation workflows and consume APIs/resources, accidental invocation can lead to unintended data sharing, cost, and unexpected execution of downstream automation.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The workflow explicitly relies on the 豆包 external API and an API key, but the skill description does not clearly warn users that their story content, prompts, and possibly generated media references may be transmitted to a third-party service. This creates a privacy and consent issue, especially if users provide sensitive, proprietary, or personal content under the assumption processing is local.

Missing User Warnings

Medium
Confidence
78% confidence
Finding
User-provided prompts and image URLs are forwarded to an external script that likely contacts a third-party media service, but the code provides no consent, notice, or boundary checks around that data transfer. In an agent-skill context, this can leak sensitive prompts, private URLs, or internal resource references to external systems without user awareness.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.