Back to skill

Security audit

短视频黄金3秒钩子生成器

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only Chinese short-video hook-writing skill with some scope and language limitations but no evident security-risk behavior.

Install this if you want Chinese short-video opening hook copy. Be aware that it may activate on broad hook or opening-related terms and will answer in a fixed Chinese format rather than adapting to other languages.

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
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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill mandates a single-language Chinese output format for all users and does not provide a language fallback or user-choice mechanism. In multilingual environments, this can lead to misunderstood instructions, inaccessible outputs, and accidental misuse, especially if the user expects another language or safety nuance is lost in translation.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger conditions include very generic terms such as “钩子”, “开场”, and “3秒”, which can appear in ordinary conversation outside the intended short-video domain. This can cause the skill to activate unexpectedly, override a more appropriate skill, or constrain the assistant into irrelevant behavior, creating scope confusion and reliability issues rather than direct code execution risk.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.