Security audit

多人对话配音 ElevenLabs Dialogue

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed wrapper for a hosted audio-generation API, with documentation quality issues but no artifact-backed malicious or review-level behavior.

Before installing, confirm you trust dLazy and the pinned @dlazy/cli package, because use requires a dLazy API key and sends your dialogue text and selected inputs to dLazy's hosted service. Expect the docs to need correction around the sample command and output type; use the documented help/options rather than the --prompt example.

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 (8)

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)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: This file presents the skill entirely in Chinese and includes agent instructions in Chinese, while not stating that Chinese is optional or that the skill is region-specific. Under the policy rule, forcing a specific language without user opt-in is a natural-language policy violation.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The help text for this skill shows an interface built around --inputs for per-line voice/text dialogue, with no --prompt option listed. However, the example invocation uses --prompt, and the error table says --prompt is a required option, which directly contradicts the documented command behavior for this dialogue tool.
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 124)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` |

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The skill is described throughout the manifest as generating multi-voice dialogue audio, but the documented JSON example shows an output object with type: "image", a .png URL, and image/png MIME type. This is an active documentation contradiction that could mislead agents or users about the actual artifact produced.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The usage section earlier documents --inputs as the primary parameter for per-line dialogue synthesis, but the example invokes --prompt, and the error table says the required missing option is --prompt <prompt>. The same error table also mentions image/video file read errors, which contradicts the skill's dialogue/audio-focused interface described elsewhere in the file.
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 124)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` |

Intent-Code Divergence

Low

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill description and usage consistently describe multi-voice dialogue audio synthesis, but the sample output declares an output object with type "image", a .png URL, and mimeType "image/png". This is not merely incomplete documentation; it actively conflicts with the intended audio-generation behavior and could mislead an agent about what the command returns.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.