ClawAudit verdict
senseaudio-let-claw-talk-universal
senseaudio-let-claw-talkv1
The skill appears to provide a legitimate functionality for setting up a continuous listening voice assistant on macOS and Windows. It uses known libraries and APIs for audio processing and speech recognition, and does not contain any obvious malicious code.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Permission integrity
package_install
Findings (5)
subprocess execution — runs system commands from Python
scripts/launch_senseaudio_let_claw_talk_universal.py · prose · downgraded · subprocess.run(
os.system/popen — direct OS command execution
scripts/start_senseaudio_let_claw_talk_universal.py · prose · downgraded · os.execv(
Python os.getenv — reads environment variable
scripts/launch_senseaudio_let_claw_talk_universal.py · prose · downgraded · os.getenv(
Python urllib.request — network access
scripts/local_senseaudio_asr.py · prose · downgraded · urllib.request
Python os.environ.get — reads environment variable
scripts/start_senseaudio_let_claw_talk_universal.py · prose · downgraded · os.environ.get(
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
Requires 1 environment variable. (1 sensitive: SENSEAUDIO_API_KEY). Requires 1 system binary.
package_install Is this flag fair?
Thanks — recorded.