Back to skill

Security audit

gemini-tts

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward RunAPI/Gemini TTS recipe that discloses its authentication, network use, paid task submission, and output verification steps.

Install this only if you are comfortable sending the text and any referenced media needed for speech generation to RunAPI and its provider path. Use an environment API key or explicit token import when possible, and review generated `request.json`, `task.json`, and downloaded outputs if the content is sensitive or billable.

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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

Static analysis

No suspicious patterns detected.