Security audit

Anime Storyboard Prompt Generation

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Markdown-only prompt-writing guide for anime storyboard prompts, with no code execution, persistence, credential use, or external data access.

Install only if you want storyboard prompt generation with Chinese-English terminology and bilingual output. Expect it to influence formatting for storyboard-related prompt tasks, but the inspected artifact does not add executables, persistence, or sensitive access.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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 (4)

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The trigger conditions are broad enough to activate on generic prompt-writing or storyboard-related requests, which can cause the wrong skill to run without clear user intent. Over-broad activation increases the chance of context hijacking, irrelevant behavior, and unintended formatting/output constraints being applied to unrelated tasks.

Natural-Language Policy Violations

Medium

Confidence: 96% confidence
Finding: Mandating bilingual Chinese-English output without user choice can override user preferences and cause unnecessary disclosure or transformation of content into another language. While not directly enabling code execution or data exfiltration, it can degrade safety and reliability by forcing unintended output behavior whenever the skill is invoked.

Natural-Language Policy Violations

Medium

Confidence: 91% confidence
Finding: The storyboard section embeds Chinese terms such as "特写分镜", "远景分镜", "中景分镜", and "动作分镜" directly into the prompt templates. Because the file does not offer an alternative language option or explain that the templates are specifically for a Chinese-language workflow, this creates a locale-specific constraint in violation of the language/locale policy criteria.

Natural-Language Policy Violations

Medium

Confidence: 83% confidence
Finding: The file consistently presents terminology with Chinese as the primary column across all sections, which constitutes a language/locale constraint in natural-language content. There is no indication that users can choose another language orientation or that the Chinese-first format is required for a region-specific use case.

Static analysis

No suspicious patterns detected.