Back to skill

Security audit

音频生成 Audio Generate

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign with medium confidence: scanners found no AIG issues, but Skillspector flagged capabilities beyond the stated audio purpose and its review was partial.

Before installing, consider whether you are comfortable with the reported visual-media features alongside audio generation and the English-only voice-search instruction. The verdict is benign, but confidence is medium and Skillspector’s assessment was partial because some referenced paths or resources could not be resolved.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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
Findings (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The code includes TTS, which aligns with part of the description, but also performs independent visual generation and enhancement workflows outside the declared audio/TTS scope. It uses hard-coded models and prompts rather than demonstrating automatic model selection based on user prompts.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The code primarily demonstrates visual-media generation and processing beyond the declared audio/TTS scope. Only one pipeline includes TTS, and the image-to-video and batch super-resolution workflows are independent visual capabilities rather than supporting audio implementation details. The commands also use fixed models and prompts rather than implementing automatic audio-model selection.

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 139)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`                                                               |

Voice searches are required to use an English descriptor without user opt-in.

Low
Category
Output Handling
Confidence
88% confidence
Finding

The instruction "Search with ONE short English descriptor" imposes a specific language on voice-search queries without offering a language choice. The explanation justifies short queries but does not document an English-only limitation that would justify the language restriction.

Content

No source excerpt is available for this finding.