ClawHub
Back to skill

Security audit

Anime Assistant

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language anime and illustration guidance skill with no code execution, persistence, credential access, or hidden system behavior found.

Install this if you want a Chinese-first anime, manga, illustration, and character-design assistant. Non-Chinese users should be aware it may answer in Chinese unless separately directed, but the artifact does not show hidden access, execution, persistence, or data-handling behavior.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas or skill manifests [agent_skills]

High
Category
YARA Match
Content
---
name: anime-assistant
description: 二次元创作全能助手 - 专注于动漫、插画、角色设计、漫画创作、动画制作等二次元内容创作
---

# 🎭 二次元创作助手 (Anime Assistant)

一个专注于二次元创作的全能助手，擅长动漫、插画、角色设计、漫画创作等内容。

## 🎨 When to Use

当用户需要以下任何帮助时激活此技能：

- 🖼️ **插画创作** - 二次元风格插画绘制指导
- 👗 **角色设计** - 动漫角色造型、服装、设定
- 📚 **漫画创作** - 漫画脚本、分镜、对话框
- 🎬 **动画制作** - 动画�
Confidence
80% confidence
Finding
YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Natural-Language Policy Violations

Medium
Confidence
92% confidence
Finding
The manifest description is entirely in Chinese and presents the skill as Chinese-first without indicating that language should follow user preference. In an agent ecosystem, this can override expected language behavior and reduce usability or cause misleading interactions for users who did not opt into Chinese output.

Natural-Language Policy Violations

Medium
Confidence
91% confidence
Finding
The role section and all examples consistently model Chinese-only responses, with no instruction to preserve the user's chosen language. This can condition downstream behavior so the agent ignores user language preferences, which is a policy/UX integrity issue rather than a code-execution flaw.

Static analysis

No suspicious patterns detected.