ClawHub
Back to skill

Security audit

录音转写 Fun ASR

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed cloud transcription wrapper, with some documentation mistakes but no artifact-backed evidence of hidden or malicious behavior.

Install only if you are comfortable using the external dLazy npm CLI and sending audio files or URLs to dLazy cloud services. Prefer `npx @dlazy/cli@1.2.3` or `DLAZY_API_KEY` for less persistent setup, review the CLI source/package if supply-chain risk matters, and be aware that the docs contain a stale `--prompt` example that should likely be `--audio_url`.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

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
94% confidence
Finding

The skill claims to perform audio transcription, but the prose also describes generic prompt submission plus image/video/audio uploads and generation outputs, which broadens the apparent behavior beyond the stated function. In an agent setting, this ambiguity is dangerous because it obscures what data may be transmitted off-host and can cause over-permissive use of the skill with sensitive local files.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The documentation for an audio transcription skill references a prompt-based interface and requires a '--prompt' parameter in examples and errors, which materially conflicts with the declared purpose and CLI options. This can mislead agents or users into invoking the wrong behavior, sending unintended data to a remote API, or trusting a capability that the skill does not actually provide.

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`                                                              |

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

L082 将 --language_code 的默认值设为 zh，且文档未说明执行前应根据用户语言偏好选择语言参数。按照自然语言/区域设置政策，默认强制特定语言而没有用户选择或显式 opt-in，属于轻微的语言/locale 策略问题。

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The documented command options for dlazy fun-asr list audio- and transcription-related flags such as --audio_url, --language_code, and diarization settings, but the example at L119 uses --prompt, and the error table at L127 says --prompt is required. This actively contradicts the surrounding documentation for an audio transcription command and indicates the docs were copied from a different skill or no longer match the actual interface.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill instructs users to persist an API key locally in a config file but does not prominently warn about credential persistence, multi-user host risk, shell history exposure, or safer secret-handling alternatives. While common, this increases the chance of accidental credential disclosure on shared systems or through backups and logs.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.