Security audit

文章转视频 Article to Video

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed wrapper around the dLazy video-generation CLI, with some scope mismatch but no hidden or destructive behavior found.

Before installing, understand that this uses an external dLazy npm CLI and hosted service: prompts are sent to dLazy, attached files are uploaded, and an API key may be saved locally. Prefer npx if you do not want a persistent global install, and avoid attaching sensitive documents unless you are comfortable with dLazy handling them.

A.I.G

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

SkillSpector

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)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 10)May include surrounding context.
md
[English](./SKILL.md) · [中文](./SKILL-cn.md)

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The manifest description at L004 scopes the skill to turning an article or text into a narrated explainer video. However, the body documentation expands the use case to PPT, Word, Excel, PDF, and general document-to-video workflows, and later states the skill is fixed to the file-to-video template, which is materially broader than article/text input.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The manifest presents this as an article-to-video skill, but the operational instructions explicitly bind it to dlazy chat --skill file-to-video, a generic file conversion template. That indicates actual behavior is centered on arbitrary file-based video generation rather than the narrower article/text-only intent stated in the manifest.
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 116)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` |

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The manifest description on L004 scopes the skill to written articles, text, news, and essays. However, the body documentation on L012 and the command template on L079/L092 describe a generic file-to-video flow supporting PPT, Word, Excel, PDF, and other documents, which is materially broader than the manifest's stated purpose.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The skill is named and described as article-to-video, but the documentation explicitly says it is pinned to the file-to-video template and instructs agents to run dlazy chat --skill file-to-video. This is an active contradiction between the skill's stated intent and its documented operational target, not merely missing detail.
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.md (reported line 116)May include surrounding context.
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` |

Static analysis

No suspicious patterns detected.