Back to skill

Security audit

数字人动作视频 即梦 Dream Actor

Security checks for vulnerabilities and agentic risk

Overview

The skill coherently supports cloud video generation and clearly discloses its media uploads, authentication, and installation requirements.

Use media you are comfortable uploading to dLazy and consider generation costs. Review the separately installed CLI, protect your API key, and use the documented dry-run option to preview requests.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
88% confidence
Finding

Authentication could be a supporting implementation detail, but the supplied code provides no connection between dlazy login and Jimeng Dream Actor and implements none of the declared conversion workflow. The assessment is limited to this chunk; its authentication mechanism and any subsequent behavior are not shown.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
87% confidence
Finding

The supplied code contains only a login command, with no image handling, video generation, or demonstrated connection to Jimeng Dream Actor. Authentication could support the declared workflow, but the supplied chunk provides no evidence of that relationship or implements the described conversion.

Content

No source excerpt is available for this finding.

Whitespace Padding

Medium
Category
Prompt Injection
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.

Content

Scanner excerpt · SKILL-cn.md (reported line 130)May include surrounding context.

md
## 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`                                                               |

Static analysis

No suspicious patterns detected.