ClawHub
Back to skill

Security audit

AI Video Script Generator (Yijia Test)

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Chinese-language AI video script and prompt template with no hidden code, persistence, or data access.

Install this if you want a Chinese-oriented helper for short-video scripts and AI video prompts. Review the optional Yijia command example before running it, especially the local /Users/shift path, API key requirement, target account, and language/category settings.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Natural-Language Policy Violations

Medium
Confidence
92% confidence
Finding
The file’s natural-language content, including the manifest description and all operating instructions, is effectively fixed to Chinese. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly documented and justified, which it is not here.

Natural-Language Policy Violations

Medium
Confidence
89% confidence
Finding
The example command hard-codes `--language zh`, which imposes a specific language/locale choice. The file does not present this as an optional user-selectable setting in the example, creating a natural-language locale policy concern.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger list is very broad and generic, covering common terms like '分镜', 'AI视频', and '视频策划' without any clear activation constraints. This can cause accidental invocation in unrelated conversations, leading to over-broad skill execution, prompt hijacking opportunities, or unexpected content generation in contexts the user did not explicitly intend.

Natural-Language Policy Violations

Low
Confidence
88% confidence
Finding
The natural-language description presents the skill in Chinese only and does not indicate that users may choose another language or locale. Per the policy criteria, forcing a specific language without opt-in is a locale/language policy concern.

Static analysis

No suspicious patterns detected.