Back to skill

Security audit

动态图形视频 Motion Graphics

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign with medium confidence: scanners report a motion-graphics skill whose instructions also include dLazy login and project-listing actions that are not clearly connected to that purpose.

The verdict is benign, but confidence is medium and Skillspector's analysis was partial: some local references were missing. Before installing, consider whether you are comfortable setting up dLazy authentication, listing organization projects, and sending messages or attached files to dLazy services, as described in the guide.

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 (7)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied code only lists organizational projects; it does not create, edit, render, or export animated graphics. Project enumeration is not described or established as a supporting step in the declared workflow.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied code only lists organization projects; it does not author, render, polish, or export animated graphics. Organization project enumeration is not declared, and the chunk provides no indication that it supports the stated animation workflow.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The supplied command initiates authentication rather than performing the declared Remotion animation workflow. Nothing in the supplied content establishes this login as a supporting implementation detail for that workflow. The command alone does not establish credential theft or other malicious behavior.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The supplied code consists solely of dlazy login. It contains no Remotion authoring, animation, polishing, or export behavior. Although authentication can support a larger workflow, the supplied content does not establish that connection. The command's exact authentication mechanism and effects cannot be determined from this snippet.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The supplied chunk only sets authentication; it contains no animation authoring, rendering, polishing, or export behavior. Authentication could support a broader workflow, but no such relationship is established here. There is no evidence in this chunk of credential exfiltration or use of a real API key.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The supplied command performs authentication configuration, not animation authoring, polishing, or export. Nothing in the chunk establishes this as a supporting step for the declared workflow. The key is a placeholder; the chunk does not demonstrate credential theft or exfiltration.

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 115)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`                                                               |