Caveat verdict
multi-agent-deployment
skill-multi-agent-deployment
This skill provides scripts and cloud deployment templates for setting up multi-agent OpenClaw fleets; the network usage is for legitimate cloud deployment (DigitalOcean, AWS, GCP) and the content is transparent infrastructure tooling with no exfiltration or hidden behavior.
⚠ 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
network_out
Findings (5)
Pipe to bash — executes piped content as shell commands
references/memory-schemas.md · code · |bash
Recursive delete from root or home — destructive command
references/troubleshooting.md · code · rm -rf /
subprocess execution — runs system commands from Python
references/workflows.md · code · subprocess.run(
References agent configuration files
scripts/agent_setup.py · prose · downgraded · AGENT_CONFIG
Popular HTTP library — network access
scripts/memory_sync.py · prose · downgraded · got
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/D/F). 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_innetwork_out Is this flag fair?
Thanks — recorded.