text-to-speech-api

• Outcome: Review
• Latest audit: May 29, 2026 at 9:35 PM UTC
• Version:
  1.0.0

Overview

This TTS skill is instruction-only, but it steers users toward a broad SkillBoss API setup and key that can enable many non-TTS paid services.

Review before installing. Use this only if you are comfortable giving SkillBoss a credential that may access many paid API categories, not just text-to-speech. Inspect the remote setup file before running it, prefer scoped keys or spending limits if available, and require explicit user approval before non-TTS calls or sending sensitive text externally.

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 Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Description-Behavior Mismatch

Medium

• Confidence: 94% confidence
• Finding: The skill is branded as a narrowly scoped text-to-speech integration, but it explicitly expands access to hundreds of unrelated APIs and capabilities. This scope mismatch can mislead users and agents into granting a broad API key and invoking capabilities far beyond TTS, increasing the chance of unintended data exposure or misuse.

Description-Behavior Mismatch

Medium

• Confidence: 95% confidence
• Finding: The agent instructions recommend unrelated chat/reasoning models and use cases inside a TTS skill. That creates dangerous ambiguity about what the agent is authorized to do and may cause an agent to route sensitive user data to non-TTS models or external services not expected by the user.

Description-Behavior Mismatch

Low

• Confidence: 88% confidence
• Finding: The discovery section markets broad access to chat, image, video, scraping, and social-data products that are unrelated to a dedicated TTS skill. While partly promotional, it still normalizes capability expansion and can encourage overbroad installation and trust in a credential with much wider reach than the skill name suggests.

Vague Triggers

Medium

• Confidence: 86% confidence
• Finding: The invocation guidance says to use the skill whenever the user needs a text-to-speech API, without defining tighter limits on data types, approved operations, or when external transmission is appropriate. In an agent setting, vague routing language can lead to overuse of the skill and unnecessary transfer of user content to a third-party API.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The setup flow encourages automatic installation and use of a key that unlocks hundreds of external APIs, but does not warn the user about the breadth of access, external data transmission, or credential sensitivity. This creates a meaningful risk of users granting expansive third-party access without informed consent or understanding of downstream exposure.

VirusTotal

65/65 vendors flagged this skill as clean.