Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md [English](./SKILL.md) · [中文](./SKILL-cn.md)
Security audit
博客转视频 Blog to Video
Security checks for vulnerabilities and agentic risk
Overview
This skill appears to be a legitimate dLazy video-generation wrapper, but it is labeled as blog-to-video while its instructions route broader document and file-to-video work to a third-party SaaS.
Review this before installing because the package is broader than its name suggests. Treat it as a general file/document-to-video SaaS integration: prompts and attached files may be sent to dLazy, and an API key may be stored locally. Only use it with documents you are allowed to upload, and verify the pinned @dlazy/cli package/source if your environment has sensitive data policies.
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
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- 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
Findings (8)
Intent-Code Divergence
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The skill is labeled as blog/article-to-video, but the body instructs use for generic document, PPT, PDF, and broader file-to-video workflows. This scope mismatch can cause the orchestrator or user to invoke the skill on inputs beyond its declared purpose, increasing the chance of unintended data upload to the third-party service and incorrect tool selection.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The trigger list contains broad generic phrases such as document-to-video and explainer-video terms that can match many common requests outside the skill's stated blog/article scope. Overbroad activation increases the risk of accidental invocation, causing unnecessary transmission of user content or files to the external CLI and service.
- Content
Description-Behavior Mismatch
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The operational instructions explicitly route requests to a broader
file-to-videoworkflow instead of a blog/article-specific flow. In practice, this can override user expectations and send arbitrary local files and prompts to the remote SaaS under a more permissive workflow than advertised.- Content
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
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` |
Description-Behavior Mismatch
Medium
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
The manifest description scopes the skill to converting a blog post or article into a narrated video. However, the body documentation expands the scope to PPT, Word, Excel, PDF, and generic document-to-video use cases, and the usage section invokes a
file-to-videotemplate rather than a blog-specific flow. This is a semantic mismatch between the declared intent and the actual documented behavior of the skill.- Content
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
md ## 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` |
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 80% confidence
- Finding
This Chinese skill file ends with an English-only tip (“Visit https://dlazy.com for more information.”), while the rest of the document is localized for Chinese users. That imposes a language choice inconsistently rather than explicitly offering the user a locale option.
- Content
Static analysis
No suspicious patterns detected.