ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified

anomaly-watcher

Continuous behavioral monitoring for OpenClaw agents. Detect anomalies in command patterns, resource usage, and skill invocations against established baselines.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/arhadnane/anomaly-watcher
Or

Anomaly 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 invocation
  • UserPromptSubmit — log input patterns
  • PostSkillExecution — log skill results

Monitored Metrics

MetricBaseline UnitAlert Threshold
Command exec frequencyper hour>2σ from 7-day avg
File access patternsunique paths/hour>2σ
Network request volumerequests/hour>2σ
Skill invocation frequencyper skill per hour>2σ
Token consumption ratetokens/hour>2σ
Error rateerrors/hour>2σ
Memory write patternswrites/hour>2σ
Cross-session messagesmessages/hour>2σ
New file creation ratefiles/hour>2σ
Unique external domainsdomains/hour>2σ

Anomaly Detection Algorithm

  1. Collect — append each action to .security/baseline/metrics.jsonl
  2. Baseline — rolling 7-day average and standard deviation per metric
  3. Compare — current window (1 hour) vs baseline
  4. Classify:
    • NORMAL — within 1σ
    • ELEVATED — between 1σ and 2σ
    • ANOMALOUS — between 2σ and 3σ
    • CRITICAL — above 3σ or matches known attack signature
  5. Alert — based on classification

Alert Actions

ClassificationAction
NORMALNo action
ELEVATEDLog to anomaly.jsonl
ANOMALOUSLog + notify human via preferred channel
CRITICALLog + 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

Author@arhadnane
Stars4473
Views0
Updated2026-05-01
View Author Profile
AI Skill Finder

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 skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-arhadnane-anomaly-watcher": {
      "enabled": true,
      "auto_update": true
    }
  }
}
Safety NoteClawKit audits metadata but not runtime behavior. Use with caution.