anomaly-watcher
Continuous behavioral monitoring for OpenClaw agents. Detect anomalies in command patterns, resource usage, and skill invocations against established baselines.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/arhadnane/anomaly-watcherAnomaly Watcher — Behavioral Baseline Monitor
Purpose
Establish a behavioral baseline for the agent and continuously monitor for deviations that may indicate compromise, misconfiguration, or abuse.
Integration
Always-on monitoring via hooks:
PostToolUse— log every tool invocationUserPromptSubmit— log input patternsPostSkillExecution— log skill results
Monitored Metrics
| Metric | Baseline Unit | Alert Threshold |
|---|---|---|
| Command exec frequency | per hour | >2σ from 7-day avg |
| File access patterns | unique paths/hour | >2σ |
| Network request volume | requests/hour | >2σ |
| Skill invocation frequency | per skill per hour | >2σ |
| Token consumption rate | tokens/hour | >2σ |
| Error rate | errors/hour | >2σ |
| Memory write patterns | writes/hour | >2σ |
| Cross-session messages | messages/hour | >2σ |
| New file creation rate | files/hour | >2σ |
| Unique external domains | domains/hour | >2σ |
Anomaly Detection Algorithm
- Collect — append each action to
.security/baseline/metrics.jsonl - Baseline — rolling 7-day average and standard deviation per metric
- Compare — current window (1 hour) vs baseline
- Classify:
NORMAL— within 1σELEVATED— between 1σ and 2σANOMALOUS— between 2σ and 3σCRITICAL— above 3σ or matches known attack signature
- Alert — based on classification
Alert Actions
| Classification | Action |
|---|---|
| NORMAL | No action |
| ELEVATED | Log to anomaly.jsonl |
| ANOMALOUS | Log + notify human via preferred channel |
| CRITICAL | Log + notify + recommend pause (human decides) |
Known Attack Signatures
- Sudden spike in file reads across many directories → possible reconnaissance
- Outbound to new external domain + high data volume → possible exfiltration
- Rapid skill installs from ClawHub → possible supply chain attack
- Memory writes with encoded content → possible persistence attempt
Guardrails
- Monitoring is strictly read-only — never modifies agent behavior
- Baseline calibration requires minimum 48 hours of data
- False positives are tracked in
.security/false-positives.jsonl - Baseline resets require human approval
- The watcher itself has no network access (local analysis only)
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-arhadnane-anomaly-watcher": {
"enabled": true,
"auto_update": true
}
}
}Related Skills
attack-surface-mapper
Purple team — map agent's full attack surface by combining red team probes and blue team detections. Identify defense coverage gaps and prioritize hardening.
audit-trail
Governance — immutable, timestamped, hash-chained audit log of all agent actions. Forensic-ready for compliance, investigation, and accountability.
bot-police
Detect, investigate, and contain malicious or compromised bots using behavior analysis, policy enforcement, and escalation protocols.