Dlazy Gemini 2.5 Tts

• Outcome: Pass
• Latest audit: Jun 2, 2026 at 10:27 AM UTC
• Version:
  1.2.0

Overview

This appears to be a disclosed cloud text-to-speech skill, with the main caution that use sends content to dLazy-hosted services.

Install only if you are comfortable with prompts and any referenced media being processed by dLazy-hosted services and with a local/API-key-based CLI workflow. Use explicit requests for TTS, avoid sending private content unless intended, and review the CLI package/source before relying on it for sensitive work.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Vague Triggers

Medium

• Confidence: 80% confidence
• Finding: Overly broad trigger keywords can cause the agent to invoke this skill on ordinary conversation, potentially sending user text to an external SaaS endpoint without sufficiently specific user intent. In this skill's context, accidental invocation is more concerning because use of the tool transmits prompts to api.dlazy.com and may rely on stored credentials, creating privacy and unintended-action risk.

Vague Triggers

Medium

• Confidence: 86% confidence
• Finding: The trigger keyword "generate speech" is ambiguous and can match a wide range of normal assistant interactions, making accidental invocation more likely. In this skill's context, accidental invocation is more concerning because the workflow explicitly transmits prompts to api.dlazy.com and may upload local media to files.dlazy.com, expanding the blast radius of a mistaken match.

Vague Triggers

Medium

• Confidence: 86% confidence
• Finding: The trigger keyword "generate speech" is ambiguous and can match a wide range of normal assistant interactions, making accidental invocation more likely. In this skill's context, accidental invocation is more concerning because the workflow explicitly transmits prompts to api.dlazy.com and may upload local media to files.dlazy.com, expanding the blast radius of a mistaken match.

VirusTotal

64/64 vendors flagged this skill as clean.