Security audit

UnlimitedTTS

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed wallet-paid text-to-speech integration with spending controls and local audio output configuration.

Before installing, configure a bounded output directory, set conservative USDC limits and approval policy, and only allow trusted payees. The skill should not receive wallet seed phrases or private keys.

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

Confidence: 87% confidence
Finding: The manifest clearly advertises wallet-paid text-to-speech and writes audio files to a configurable output directory, but it does not present an explicit user-facing warning or consent notice about spending funds or creating local files. In an agent setting, this can lead to unexpected payments or disk writes triggered through normal tool use, especially if users or operators assume the plugin is non-spending or side-effect free.

Static analysis

No suspicious patterns detected.