Caveat verdict
agent-dashboard-v2
digital-staff-dashboard
Serves a local web dashboard on port 5181 for managing OpenClaw agents; the execution sink is the local Python HTTP server which is appropriate for a dashboard tool, and all features (agent monitoring, skill management, dispatch) match the stated 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.
Findings (9)
Recursive delete from root or home — destructive command
SKILL.md · code · rm -rf ~
Accesses OpenClaw config/secrets directly
SKILL.md · prose · downgraded · ~/.openclaw/openclaw.json
References agent configuration files
OPENCLAW_SCHEMA_README.md · code · agent_config
HTTP request to bare IP address — common in malicious payloads
config.py · prose · downgraded · http://127.0.0.1
subprocess execution — runs system commands from Python
dashboard_server.py · prose · downgraded · subprocess.run(
References sudo — requests elevated privileges
open_port.sh · prose · downgraded · sudo
pip3 install — installs Python packages at runtime
README.md · code · pip3 install
Python shutil file operation — copies/moves/deletes files
openclaw_config.py · prose · downgraded · shutil.rmtree(
Python os.environ.get — reads environment variable
openclaw_finder.py · prose · downgraded · os.environ.get(
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
No declared permissions — minimal attack surface.
network_in Is this flag fair?
Thanks — recorded.