Caveat verdict
mm-voice-maker
MiniMax Voice API skill for TTS, voice cloning, and audio processing; transparently documents that uploaded audio is sent to MiniMax's servers and advises against uploading sensitive content — behavior matches purpose.
⚠ 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.
Permission integrity
package_install
Findings (9)
Possible hardcoded credential
SKILL.md · code · API_KEY="your-api-key-here
References sudo — requests elevated privileges
SKILL.md · code · sudo
Downloads executables from external URLs
reference/api_documentation.md · code · Download from https://
Opens WebSocket connection
SKILL.md · code · WebSocket
subprocess execution — runs system commands from Python
check_environment.py · prose · downgraded · subprocess.run(
Accesses shell history/config
check_environment.py · prose · downgraded · ~/.zshrc
Python os.getenv — reads environment variable
reference/troubleshooting.md · code · os.getenv(
Popular HTTP library — network access
reference/troubleshooting.md · prose · downgraded · got
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_accessnetwork_inpackage_install Is this flag fair?
Thanks — recorded.