ClawHub
Back to skill

Security audit

漫剧动态动画

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-writing skill for turning comic storyboards into short image-to-video animation prompts, with no code, credential use, file access, or hidden execution behavior.

Installers should understand that this skill is meant for Chinese-language comic animation prompt workflows and may activate on broad animation-related requests; otherwise its behavior is limited to generating prompt text and tool parameter suggestions.

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
  • 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
93% confidence
Finding
The trigger list includes generic terms such as “动态”, “动画”, and “让画面动起来”, which are broad enough to match ordinary user requests outside the intended skill scope. In an agentic system that auto-selects skills, this can cause unintended invocation, prompt-routing errors, or priority hijacking, especially since the metadata says the skill may be automatically called by another workflow.

Natural-Language Policy Violations

Low
Confidence
72% confidence
Finding
The skill description and instructions are primarily fixed in Chinese, while some prompt structures are specified in English, and the file does not state that users may choose their preferred language. This can create an implicit language policy without opt-in, which falls under locale/language policy concerns.

Static analysis

No suspicious patterns detected.