视频生成 通义万相 Wan 2.7

• Outcome: Pass
• Latest audit: Sep 14, 2026 · 1:44 AM UTC
• Version: 1.3.15

Overview

This skill is a disclosed wrapper for a third-party video-generation CLI, with expected API-key storage and cloud media upload behavior.

Before installing, users should understand that this invokes a third-party dLazy cloud service, may upload any media files they pass as inputs, and can store a dLazy API key locally. Use npx if you do not want a persistent global CLI install, and only pass media files you intend to send to dLazy.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Ae1

High

• Category: analysis-evasion

Content

[English](./SKILL.md) · [中文](./SKILL-cn.md)

• Confidence: 100% confidence
• Finding: Referenced artifact was not completely inspected

Vague Triggers

Medium

• Confidence: 96% confidence
• Finding: The trigger keyword list includes the very broad everyday phrase “视频生成”, which can cause the skill to activate in many unrelated conversations about video generation. Over-broad activation increases the chance an agent invokes an external CLI, uploads local media paths, or prompts for credentials when the user did not explicitly intend to use this third-party service.

Whitespace Padding

Medium

• Category: Prompt Injection

Content

## 错误处理

| Code | 错误类型                         | 示例信息                                                                                                                 |
| ---- | -------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |
| 401  | 未授权 (API Key缺失或无效)       | `ok: false, code: "unauthorized", message: "API key is missing or invalid"`                                                              |
| 501  | 缺少必填参数                     | `error: required option '--prompt <prompt>' not specified`                                                               |

• Confidence: 70% confidence
• Finding: Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.

Vague Triggers

Medium

• Confidence: 96% confidence
• Finding: The trigger keyword "video generation" is overly generic and can cause this skill to activate for broad, unrelated user requests that merely mention generating video. In an agent ecosystem, overbroad matching can route users into a third-party SaaS workflow unexpectedly, leading to unintended command execution, cloud uploads of local media paths, and unnecessary credential/API use.

Whitespace Padding

Medium

• Category: Prompt Injection

Content

## Error Handling

| Code | Error Type                         | Example Message                                                                                                          |
| ---- | ---------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |
| 401  | Unauthorized (No API Key)          | `ok: false, code: "unauthorized", message: "API key is missing or invalid"`                                                              |
| 501  | Missing required parameter         | `error: required option '--prompt <prompt>' not specified`                                                              |

• Confidence: 70% confidence
• Finding: Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.

Static analysis

No suspicious patterns detected.