Back to skill

Security audit

短视频创作全能工具

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language short-video, lyrics, and style-consistency guide with no evidence of hidden execution, credential access, persistence, or data exfiltration.

Install this if you want a Chinese-language workflow for short-video scripts, lyrics, anime-style prompts, and character consistency. Review the broad triggers if you use many creative-writing skills, and require confirmation before any tool uploads media, calls external music/video services, or runs FFmpeg commands.

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
87% confidence
Finding

The metadata and trigger text are entirely Chinese and do not indicate any language options or justified locale restriction. This is primarily a safety and usability issue because users may be routed into a language-specific skill they cannot understand, which can lead to misinterpretation of outputs or accidental acceptance of actions.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list includes very generic creative phrases such as '写剧本', '写歌词', '创作视频', and '写歌', which are common user intents across many benign contexts. This can cause unintended activation of the skill, pulling users into a workflow they did not explicitly request and increasing the chance of prompt/skill routing abuse or accidental execution of unrelated tool instructions.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list is broad and contains common creative terms such as '写剧本', '写歌词', '写歌', and '二次元', which can cause the skill to activate in many unrelated conversations. Unintended activation can expose users to unexpected tool behavior, override more appropriate skills, or increase the chance that downstream risky functionality is invoked without clear user intent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file presents all instructions and examples exclusively in Chinese, which can impose a specific language on users without opt-in. The policy allows locale constraints only when explicitly offered as a choice or clearly justified as region-specific, neither of which is stated here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

SQP-3 applies to all file types and covers language or locale policy violations. This markdown guide presents all instructions and labels only in Chinese, with no indication that the user can choose another language or that the Chinese-only format is required for a justified region-specific context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The document instructs users to standardize outputs with terms like "anime style" and "2D Japanese animation," effectively prescribing a specific cultural/locale style as the default. Under the stated policy, forced locale-specific constraints should either be optional or clearly justified, and no such opt-in or justification is provided here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file presents all headings and most descriptive content exclusively in Chinese, which can amount to a language/locale restriction for users who do not read Chinese. The file does not indicate that the skill is region-specific or provide any user opt-in or alternative language support.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

The entire skill reference is written only in Chinese and does not indicate that the user can choose another language or that the content is intended solely for a China-specific audience. Under the stated policy, forcing a specific language without opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

This markdown file is written entirely in Chinese and does not indicate that users may choose another language or that the content is intentionally limited to a Chinese-speaking audience. Under the language/locale policy rule, a skill should not force a specific language without opt-in unless the restriction is clearly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The entire guide is presented in Chinese and does not indicate that users may choose another language or that the skill is intentionally limited to a Chinese-speaking audience. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.