Security audit

Anime Drama Studio

Security checks across malware telemetry and agentic risk

Overview

This is a Chinese-language creative writing workflow skill for anime drama scripts and storyboards, with no code execution, persistence, credential access, or hidden data handling.

Installers should expect this skill to respond mainly in Chinese and to activate for broad script or storyboard creation requests. Review generated creative prompts before using them in image or video tools, but no privileged local or account access is requested by the skill itself.

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 (2)

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The trigger description includes broad everyday phrases such as “写剧本” and “生成分镜,” which can match many ordinary requests beyond the intended scope. This can cause accidental skill invocation, routing user content into a highly prescriptive workflow and increasing the chance of inappropriate handling of unrelated prompts or prompt-surface expansion.

Natural-Language Policy Violations

Medium

Confidence: 82% confidence
Finding: The skill metadata and content are written as if the interaction will occur in Chinese, without offering language negotiation or stating clear limits. In multilingual environments, this can lead to incorrect routing, degraded user comprehension, and unsafe or misleading outputs if users receive content in a language they did not request or cannot verify.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.