Back to skill

Security audit

录音转写 Fun ASR

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign with medium confidence: the scanners found no AIG issues, while Skillspector flagged an unexplained CLI login and incomplete evidence connecting the reported commands to the stated transcription purpose.

Consider that the verdict is benign, not a guarantee of safety. Skillspector's scan was partial: it reported unresolved local references and did not inspect the external CLI package implementation. Before installing, review what `dlazy login` does and whether the CLI is the service you intend to use; avoid entering credentials unless you trust that service.

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
  • 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 (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The supplied code only invokes dlazy login; it does not process recordings or invoke a demonstrated Fun-ASR service. Authentication could support a transcription workflow, but nothing in this chunk establishes that connection. The observed behavior therefore does not match the declared purpose. The command alone does not establish what credentials or resources it accesses.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

The only supplied operation is a login command, rather than transcription. Authentication could support a transcription service, but this chunk provides no evidence connecting dlazy login to Alibaba Bailian Fun-ASR. The visible behavior therefore differs from the declared purpose; credential handling and other side effects cannot be determined from this command alone.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
78% confidence
Finding

The only supplied command does not identify an ASR operation, audio input, Alibaba service integration, language detection, or diarization. Instead, it invokes an external CLI with a placeholder command. The package could conceivably provide supporting transcription functionality, but its implementation is not supplied, so that connection cannot be verified. This assessment does not assume the package is malicious.

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`                                                               |