Security checks across malware telemetry and agentic risk
This is a real TTS voice-reply skill, but it needs review because it can automatically send replies and voice samples to Noiz, store files and an API key locally, install a dependency at runtime, and exposes broader voice-cloning/timeline features than the description makes clear.
Review before installing. Use this only if you are comfortable with assistant reply text, optional reference audio, and possibly subtitle text being sent to Noiz; generated audio being saved and played locally; previous generated audio being deleted; and a Noiz API key being stored in your home directory. Install dependencies yourself from trusted sources and avoid reference-audio URLs or save_voice unless you intentionally want remote voice-cloning behavior.
def ensure_noiz_ready() -> None:
if importlib.util.find_spec("requests") is None:
print("[noiz] Installing requests...", file=sys.stderr)
subprocess.check_call(["uv", "pip", "install", "requests"])
def detect_text_lang(text: str) -> str:def ensure_noiz_ready() -> None:
if importlib.util.find_spec("requests") is None:
print("[noiz] Installing requests...", file=sys.stderr)
subprocess.check_call(["uv", "pip", "install", "requests"])
def detect_text_lang(text: str) -> str:66/66 vendors flagged this skill as clean.