ClawHub
Back to skill

Security audit

语音合成 通义 Qwen TTS

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed dLazy Qwen TTS CLI skill with expected API key and network use, though parts of the documentation appear copied from another media tool.

Before installing, confirm you are comfortable running the pinned external dLazy CLI, sending prompts to dLazy's hosted API, and storing a revocable dLazy API key locally. Treat the image-output examples as documentation errors and verify actual qwen-tts output behavior with dlazy qwen-tts -h or a dry run.

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 (6)

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)

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill is described throughout the manifest as a text-to-speech tool, which implies audio output, but the documented JSON example shows an output of type "image" with a PNG URL and MIME type. This is an active contradiction in the file’s own documentation, not merely an omission, and can mislead an agent about what the command actually returns.

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 125)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`                                                               |

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 125)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
98% confidence
Finding

The manifest and usage describe a text-to-speech skill, so its output should be audio. However, the documented JSON example shows an output of type "image" with a PNG URL and mime type, which actively conflicts with the intended behavior rather than merely omitting detail.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The documented CLI options for this skill only expose text prompt, voice, language, and save-path parameters for text-to-speech generation. The error table’s "Local file read error" example mentions image/video files, which conflicts with the described interface and suggests copied documentation from a different media skill.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.