ClawHub
Back to skill

Security audit

viral-script-writer

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language short-video script writing skill with no code execution, data access, persistence, or hidden install behavior.

Use this if you want Chinese-language social video script templates. Because it includes persuasive hook formulas and growth-oriented calls to action, review generated copy for truthfulness, audience fit, and platform policy compliance before publishing.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 is fully written in Chinese without an advertised language-selection mechanism or a documented locale restriction, which can cause misrouting, misunderstanding of instructions, or opaque behavior for users and orchestrators expecting multilingual compatibility. While not directly enabling code execution or exfiltration, it can degrade safety by making the skill’s scope and outputs less transparent in mixed-language environments.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The activation description is broad enough to match many generic writing requests such as scripts, copy, or short-form content, which can cause unintended skill invocation. That increases the chance the agent applies specialized persuasive-growth tactics in contexts where the user did not explicitly request this behavior, leading to prompt-routing errors and overreach.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.