Back to skill

Security audit

分镜脚本 Storyboard

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign because most dimensions are marked ok, while noting an install-related caveat; confidence is medium and the scan evidence is incomplete.

The verdict is benign, but benign does not mean risk-free. Before installing, consider the reported login and project-listing actions and the referenced CLI install and service data handling. Some referenced details were missing from the scan, so the evidence is incomplete.

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 (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied code only lists organization projects; it performs none of the described animation or video-production tasks. No connection is shown that would make project enumeration a supporting implementation detail of the declared workflow.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The supplied code only lists organization projects. It performs no animation or video-production work and shows no connection between project enumeration and the declared workflow. Based on this chunk, the behavior is materially different from the stated purpose.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
92% confidence
Finding

The supplied code only invokes a login command; it contains no storyboard, character, video, audio, subtitle, or rendering operations. Authentication could support a larger workflow, but the supplied material establishes no connection between dlazy and the declared purpose. No credential theft or other additional behavior can be inferred from this command alone.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
87% confidence
Finding

Authentication could support a video-production workflow, but the supplied chunk contains only the login command and no connection to the declared production tasks. As supplied, its primary behavior does not match the description. There is no evidence here of credential theft, exfiltration, or other hidden behavior.

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`                                                               |