text-to-speech

Pass

Audited by Gen Agent Trust Hub on Nov 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches the official CLI installer and configuration tools from ElevenLabs' GitHub repository and official website.
  • [REMOTE_CODE_EXECUTION]: Provides instructions to execute a shell script from the vendor's release page for CLI installation, which is a standard procedure for this tool.
  • [COMMAND_EXECUTION]: Demonstrates the use of subprocess in Python to pipe audio streams to ffplay for real-time playback, which is consistent with the skill's purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes arbitrary text input for conversion to speech. While this represents an injection surface where an attacker could potentially use audio tags (e.g., [whispers]) to manipulate the output tone, the result is audio data and does not pose a risk to the agent's execution logic or system security.
  • [CREDENTIALS_UNSAFE]: References the use of ELEVENLABS_API_KEY but adheres to security best practices by recommending environment variables and providing an automated CLI onboarding process (onboard init) to avoid manual handling of secrets.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 10, 2026, 11:02 PM