ClawHub
Back to skill

Security audit

漫剧工坊

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward creative-writing helper that reads a user-provided manga-drama link and turns the available content into an original story outline and storyboard script.

Before installing, users should understand that the skill may fetch and summarize links they provide. Avoid giving it private, login-only, or sensitive URLs unless you are comfortable with the agent trying to read them, and review generated adaptations for copyright or platform-policy suitability.

SkillSpector

By NVIDIA
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
91% confidence
Finding
The skill description is broad enough that it may activate on loosely related requests such as general script writing or adaptation help, causing the agent to invoke this skill when the user did not clearly intend link-based manga-drama transformation. Overbroad activation can lead to inappropriate tool use like fetching arbitrary URLs and producing outputs based on irrelevant or incomplete source material.

Vague Triggers

Low
Confidence
84% confidence
Finding
The marketing-style phrasing encourages casual use ('扔进来，自动提取内容') without clearly defining boundaries, exclusions, or prerequisites. This increases the chance of accidental invocation and silent scope expansion, especially for users mentioning inspiration from a manga short without actually wanting link analysis or derivative generation.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.