speech

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE_EXFILTRATION]: The skill securely handles API credentials by instructing the user to set the OPENAI_API_KEY as an environment variable rather than pasting it into the chat. The bundled script reads the key directly from the environment.
  • [EXTERNAL_DOWNLOADS]: Dependencies are limited to the well-known openai Python package from a trusted organization. No untrusted third-party scripts or binaries are downloaded.
  • [REMOTE_CODE_EXECUTION]: The skill uses a local, inspectable Python CLI script (scripts/text_to_speech.py) to perform its tasks. It does not execute arbitrary code from remote sources or use dangerous functions like eval() or exec().
  • [INDIRECT_PROMPT_INJECTION]: While the skill processes user-supplied text to generate audio, it implements character limits and relies on a structured workflow to ensure the input is treated as data for the TTS engine rather than instructions for the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 06:56 AM
Security Audit — agent-trust-hub — speech