minimax-tts-send

• Outcome: Review
• Latest audit: May 29, 2026 · 9:26 PM UTC
• Version: 1.0.1

Overview

This skill does the MiniMax text-to-speech work it advertises, but it embeds a provider API key and sends user text to an external service without clear credential or privacy disclosure.

Review before installing. Use this only if you are comfortable sending the text you enter to MiniMax, and replace the embedded API key with your own configured credential after the publisher rotates the exposed key. Confirm any messaging channel and recipient before sending generated audio.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands

Findings (7)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 90% confidence
• Finding: The skill documentation instructs use of both network access and shell commands, but no explicit permissions are declared. That creates a transparency and trust problem: users or orchestration systems cannot accurately assess that the skill can contact external services and invoke local commands before use.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 96% confidence
• Finding: A description-behavior mismatch is a serious security issue here because the skill reportedly hardcodes and uses an API key and claims capabilities that are either broader or different from what is clearly disclosed. Hidden credential use and undisclosed functionality undermine informed consent, make abuse harder to detect, and can expose secrets or trigger unintended external actions.

Context-Inappropriate Capability

High

• Confidence: 99% confidence
• Finding: The script contains a hard-coded MiniMax API key directly in source code, which is a real secret exposure. Anyone with access to the skill code can reuse the credential to make API calls, incur charges, abuse the account, or access associated service data, and the credential is unrelated to any secure user-mediated secret handling.

Missing User Warnings

Medium

• Confidence: 85% confidence
• Finding: The markdown explicitly describes sending outbound messages with generated audio to third-party channels but provides no warning about privacy, consent, destination verification, or potential data leakage. In a messaging-capable skill, that omission increases the risk of users transmitting sensitive content or contacting unintended recipients through external platforms.

Missing User Warnings

High

• Confidence: 98% confidence
• Finding: The skill silently uses an embedded API credential without informing the user, which hides sensitive credential usage and prevents informed consent. This makes the exposed secret easier to misuse and obscures the fact that the skill is operating under the author's or another party's account.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The skill sends user-provided text to a third-party TTS API, which is expected for cloud TTS functionality, but it does so without an explicit warning or consent prompt about outbound data sharing. If users provide sensitive or private text, that content will leave the local environment and be processed by an external service.

External Transmission

Medium

• Category: Data Exfiltration

Content

try:
        print(f"正在生成语音...", file=sys.stderr)
        resp = requests.post(url, headers=headers, json=data, timeout=60)
        resp.raise_for_status()
        result = resp.json()

• Confidence: 88% confidence
• Finding: requests.post(url, headers=headers, json=

VirusTotal

66/66 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.