ClawHub
Back to skill

Security audit

漫剧剪辑合成

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only comic-video editing guidance skill with no evidence of code execution, data access, credential use, persistence, or destructive behavior.

Install only if you want an agent to help produce Chinese comic-video post-production plans. Because its trigger words are broad, review workflow routing if you use manju-workflow so ordinary editing requests do not invoke it unexpectedly.

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 (1)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger list includes very generic terms such as 剪辑、后期、合成、字幕、BGM、导出, which are common in normal conversation about media work and can cause unintended activation. In a workflow-integrated skill that can be auto-invoked by manju-workflow, overly broad triggers increase the chance of the wrong skill being selected, leading to incorrect execution context, confusion, or unintended downstream actions.

Static analysis

No suspicious patterns detected.