Destructive delete command
Warn
- Finding
- Documentation contains a destructive delete command without an explicit confirmation gate.
status-monitor
Security checks across static analysis, malware telemetry, and agentic risk
Overview
The skill appears purpose-aligned, but it stores a monitoring token and runs a periodic/background uploader that sends your OpenClaw agent IDs to the configured dashboard.
Before installing, confirm you trust the monitoring dashboard and are comfortable with it receiving your agent IDs and online heartbeats. Protect or rotate the generated token, verify the monitor URL, review the full untruncated script if installing from a repository, and stop the daemon before uninstalling.
Static analysis
VirusTotal
VirusTotal findings are pending for this skill version.
Risk analysis
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
What this means
The agent and local skill files will handle a service token; anyone with access to that token may be able to upload or manipulate monitoring status for the account.
Why it was flagged
The skill intentionally asks the user to provide a monitoring-platform token and stores it locally for later uploads.
Skill content
Wait for user to reply with token ... Save to ~/.openclaw/credentials/openclaw-status-monitor.json: { "agentToken": "user-provided-token" }Recommendation
Only provide a token generated for this monitoring service, keep the credential file protected, and rotate or revoke the token when uninstalling or if exposure is suspected.
What this means
The monitoring service can learn your OpenClaw agent IDs and heartbeat timing, which may reveal your agent inventory and online status.
Why it was flagged
The uploader sends the local agent ID list and monitoring token to the configured dashboard API.
Skill content
url = f"{get_monitor_url()}/api/upload" ... agents = [{"id": aid} for aid in agent_ids] ... "x-agent-token": tokenRecommendation
Verify the monitor URL is the intended HTTPS dashboard, and enable the skill only if you are comfortable sharing agent IDs and heartbeats with that service.
What this means
After setup, the uploader may keep running and sending status updates at the configured interval until stopped.
Why it was flagged
The skill is designed for periodic or background operation, which is expected for status monitoring but should be visible to users.
Skill content
OpenClaw's built-in cron executes the script periodically ... Use `--fork` to start a real background daemon
Recommendation
Use the documented stop/status commands to manage it, and stop the service before uninstalling or if you no longer want cloud status uploads.
What this means
It may be harder to confirm the reviewed package matches the intended upstream project or future manual installs.
Why it was flagged
The registry metadata does not provide a clear source or install contract for a skill that includes a runnable background uploader.
Skill content
Source: unknown; Homepage: none; No install spec — this is an instruction-only skill.
Recommendation
Install only from a source you trust, compare the full script against the reviewed files, and prefer pinned or official releases when available.