ClawHub
Back to skill

Security audit

漫剧美术总监

Security checks for vulnerabilities and agentic risk

Overview

This skill only provides comic art prompt-writing instructions; its broad triggers may be noisy but no unsafe capabilities were found.

Install this if you want a Chinese-language comic art prompt workflow with fixed 9:16 prompt conventions. Be aware that broad terms like art, character design, and scene design may activate it more often than desired, and Stable Diffusion output is prescribed in English tag style.

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
  • 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
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger list includes broad, common terms such as “美术”, “角色设计”, and “场景设计”, which can match ordinary user requests and cause this skill to activate outside its intended scope. Because the skill is also described as callable automatically by another workflow, overbroad activation increases the chance of unintended prompt injection of rigid formatting/tool rules into unrelated tasks and can disrupt downstream agent behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill hard-codes output conventions for specific tools and language formats, including requiring Chinese full descriptions for some tools and English tag format for Stable Diffusion, without any user-language preference or opt-in mechanism. This can override user expectations, reduce usability, and create control-flow issues in larger workflows where downstream components expect different languages or schemas.

Content

No source excerpt is available for this finding.