Back to skill

Security audit

Video Script Writer

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only Chinese short-video script-writing skill with no code execution, credential access, persistence, or hidden data movement.

Install this if you want Chinese short-video script help for the named platforms. Be aware it strongly defaults to Chinese output and its broad trigger terms may activate for some general script-writing requests, so users who need multilingual or non-video writing may prefer a narrower skill.

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 (10)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description explicitly presents the skill as a Chinese short-video script assistant, and the usage examples are all in Chinese. There is no indication that users may choose another language or that the Chinese-only scope is a documented, justified regional requirement.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The activation criteria include very broad terms such as '脚本', '教程类内容创作', and general content-creation scenarios, which can cause the skill to be selected in contexts far beyond short-video writing. Over-broad routing is dangerous because it can misapply domain-specific instructions, suppress better-matched skills, or cause unintended handling of unrelated user content.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

L139 明确规定“所有脚本用中文写作”,属于强制单一语言输出的自然语言策略约束。文件中未提供用户选择其他语言的选项,也未说明该限制仅适用于特定中文地区合规场景,因此构成语言/locale policy 风险。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The document title and directive state platform adaptation rules entirely in Chinese and use mandatory language such as '脚本必须做平台级适配'. In this skill context, the file appears to impose a specific language/locale convention without indicating that users may choose another language, which matches the language/locale policy violation category.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

This markdown test file presents all instructions, inputs, and expected outputs exclusively in Chinese. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation, and the file does not provide any language selection or explain a region-specific constraint.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

L038 的“告诉我主题和目标平台”是较宽泛的触发说明,只要用户提到主题和平台,理论上就可能匹配,但没有说明必须是短视频脚本生成场景。缺少负面示例或限定条件时,容易与一般内容策划、发帖建议等请求混淆。

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

L054 只要求用户提供主题即可触发,但“主题”本身适用于大量写作、营销和创意任务,不足以限定在短视频开头生成。缺少平台、内容形态或输出边界说明,存在误触发风险。

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

L066 的“已有脚本”可以指代视频脚本、代码脚本、戏剧脚本等多种对象,而该技能实际目标是短视频脚本优化。未明确限定“短视频脚本”会降低触发判定的清晰度。

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The instruction accepts arbitrary long text or long video content and promises conversion into short-video scripts without constraining content type, source, or domain. That broad intake can lead to accidental activation on unrelated or sensitive material and may cause the skill to transform content it was not meant to process, increasing the chance of privacy, policy, or routing errors.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file presents all instructions, examples, and templates only in Chinese, and does not indicate that the skill is intended exclusively for Chinese-speaking users or provide any user opt-in for language selection. Under the language/locale policy, forcing a specific language without user choice can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.