Back to skill

Security audit

全能视频生成 可灵 Kling V3 Omni

Security checks for vulnerabilities and agentic risk

Overview

The skill openly describes login, media uploads, and paid video generation that fit its stated purpose.

Use media you are comfortable uploading to dLazy and account for generation charges. Review the pinned third-party CLI before installing, prefer device login over pasting keys into commands, and revoke stored keys when no longer needed.

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 (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding

The supplied code only invokes a login command and contains no Kling model invocation, multimodal input handling, or video generation. Authentication could support a larger workflow, but no such connection is demonstrated here. This assessment does not imply credential theft or other unobserved behavior.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding

Authentication setup could legitimately support video generation and is not inherently an undeclared capability. However, it is the entire supplied implementation: there is no Kling invocation, input processing, or video-generation request. The code therefore does not implement the declared primary purpose.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
88% confidence
Finding

The entire supplied chunk is an authentication command; it contains no video-generation invocation or handling of image or prompt inputs. Authentication could support a larger generation workflow, but no such connection is established in the supplied code. There is no evidence that login succeeds or that credentials are accessed.

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 136)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.