Security audit

Anime Storyboard Prompt Generation

Security checks across malware telemetry and agentic risk

Overview

This is a markdown-only prompt-writing skill for anime storyboard prompts, with no evidence of code execution, data access, persistence, or hidden behavior.

Installers should expect this skill to add structured anime storyboard prompt templates, negative prompt suggestions, and often bilingual output. Review the output format if you need single-language or machine-parseable responses.

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 (2)

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The trigger scenarios are broad enough to match common, everyday user phrasing such as requests to learn prompt writing techniques or general storyboard-related needs. This can cause unintended invocation of the skill, leading to irrelevant activation, prompt hijacking opportunities across unrelated conversations, or bypass of more appropriate specialized skills.

Natural-Language Policy Violations

Medium

Confidence: 88% confidence
Finding: Mandating bilingual Chinese-English output without user opt-in can cause the skill to override user preferences and disclose more content than necessary in contexts where only one language was requested. While not directly enabling code execution or data exfiltration, it increases the chance of policy misalignment, unnecessary token usage, and accidental leakage of translated sensitive content into an additional language.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.