ClawHub
Back to skill

Security audit

Crazyrouter Tts

Security checks across malware telemetry and agentic risk

Overview

This skill does what it claims: it converts user-provided text to speech through Crazyrouter and saves the requested audio file.

Install only if you are comfortable sending the text you synthesize to Crazyrouter. Avoid using it for secrets, private documents, regulated data, or account credentials, and do not set CRAZYROUTER_BASE_URL unless you intentionally trust that endpoint.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The skill description is broad enough to match common user requests like 'read aloud' or 'generate audio' without clearly constraining what content may be sent to the external provider. In an agent setting, this can cause over-triggering and unintended transmission of sensitive user text to Crazyrouter, especially when the user did not explicitly consent to using a third-party TTS service.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill does not warn users that supplied text is transmitted to an external API and that synthesized speech is written to a local output file. This creates a privacy and data-handling risk because users may provide confidential content assuming processing is local, while the agent instead exfiltrates it to a third party and persists the result on disk.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.env_credential_access

Environment variable access combined with network send.

Critical
Code
suspicious.env_credential_access
Location
scripts/main.mjs:7