飞书发语音(edge)

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:15 PM UTC
• Version:
  1.0.1

Overview

This skill appears to do what it advertises: turn text into speech with Edge TTS and send the audio to Feishu.

Install only if you intend to send generated voice messages to Feishu. Do not enter passwords, tokens, regulated data, or confidential incident details unless you are comfortable with Edge TTS processing the text and Feishu receiving the resulting audio. Confirm the target chat before sending.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 84% confidence
• Finding: The skill documentation exposes capabilities that imply environment access, file writing, and shell execution, but it does not declare permissions or boundaries for those actions. In an agent setting, this weakens user awareness and policy enforcement, making it easier for the skill to invoke local commands or write files without explicit consent expectations.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The README instructs users to convert text to speech and send it to Feishu, but it does not warn that the message content and generated audio will be transmitted over external services and may leave the local machine. In a messaging/notification skill, users may paste alerts, secrets, or operational data, so the lack of a clear disclosure increases the risk of inadvertent data exposure.

Vague Triggers

Medium

• Confidence: 80% confidence
• Finding: The trigger phrases are generic terms like “tts” and “文字转语音,” which can match many benign user requests and unintentionally activate this skill. That increases the chance of surprise execution involving external tooling and message delivery to Feishu when the user did not clearly intend to use this specific integration.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The description does not clearly warn users that input text is sent through external TTS tooling and that the resulting audio is delivered to Feishu, which may involve sensitive content leaving the local context. Without an explicit disclosure, users may unknowingly submit confidential text to third-party services or enterprise messaging destinations.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The skill sends user-provided text to Edge TTS, which is an external network service, without clearly warning the user that message contents leave the local environment. In a messaging workflow, users may supply sensitive operational or personal text, so undisclosed transmission creates a real privacy and data-handling risk.

VirusTotal

66/66 vendors flagged this skill as clean.