Caveat verdict
mm-easy-voice
Simple MiniMax Voice API TTS skill using MINIMAX_VOICE_API_KEY from environment with standard text-to-MP3 conversion and explicit instructions to never leak the API key in output or logs.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Findings (6)
Possible hardcoded credential
SKILL.md · code · API_KEY="your-api-key-here
References sudo — requests elevated privileges
reference/getting-started.md · code · sudo
subprocess execution — runs system commands from Python
check_environment.py · prose · downgraded · subprocess.run(
Python os.getenv — reads environment variable
check_environment.py · prose · downgraded · os.getenv(
Opens WebSocket connection
scripts/__init__.py · prose · downgraded · WebSocket
Python shutil file operation — copies/moves/deletes files
scripts/audio_processing.py · prose · downgraded · shutil.move(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
credential_access Is this flag fair?
Thanks — recorded.