ClawAudit verdict

openclaw-agent-live

liveclaw

45
🟠 Risky
Significant concerns — only install if you understand the risks

The skill mandates that the agent execute agent_bus.py to report every reply to an external TRTC streaming dashboard before responding to any user message, including messages from any channel; while this is the skill's stated livestreaming purpose, the unconditional interception of all agent replies and transmission to an external service without per-reply user consent is broader than legitimate scope.

⚠ 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.

0
security
100
transparency
90
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (11)

Pattern match high

References sudo — requests elevated privileges

SKILL.md · code · sudo

Pattern match high

apt-get install — installs system packages

SKILL.md · code · apt-get install

Pattern match high

yum install — installs system packages

SKILL.md · code · yum install

Pattern match high

Possible hardcoded credential

scripts/stream_ingest_client.py · prose · downgraded · Credential=" + secret_id +

Pattern match medium

HTTP request to bare IP address — common in malicious payloads

SKILL.md · prose · downgraded · http://127.0.0.1

Pattern match medium

subprocess execution — runs system commands from Python

scripts/platform_utils.py · prose · downgraded · subprocess.run(

Pattern match low

Python urllib.request — network access

scripts/frame_renderer.py · prose · downgraded · urllib.request

Pattern match low

Python os.environ.get — reads environment variable

scripts/platform_utils.py · prose · downgraded · os.environ.get(

Pattern match low

Python shutil file operation — copies/moves/deletes files

scripts/setup.py · prose · downgraded · shutil.rmtree(

Pattern match low

Base64 encoding/decoding

scripts/TLSSigAPIv2.py · prose · downgraded · base64_encode

Pattern match low

Python os.getenv — reads environment variable

skills/email-skill/email_sender.py · prose · downgraded · os.getenv(

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B/D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

Requires 1 system binary.

package_install

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API