Monitor Alert - Automaton Edition

• Outcome: Review
• Latest audit: May 29, 2026 at 9:26 PM UTC
• Version:
  1.0.0

Overview

This is mostly a health-monitoring skill, but it includes under-disclosed local workspace inspection and persistent edits to agent session state.

Install only if you are comfortable with a monitoring skill that reads local OpenClaw workspace state and can edit SESSION-STATE.md. Review or disable token-monitor.js unless you specifically want token-budget status persisted into future agent session context.

SkillSpector

By NVIDIA

Vulnerability Patterns

• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 88% confidence
• Finding: The skill’s documented purpose is limited to system health monitoring and alerting, but the finding indicates it also scans unrelated skill directories and modifies SESSION-STATE.md. Undocumented filesystem inspection and state mutation expand the skill’s effective privileges and can create integrity and privacy risks, especially if operators invoke it expecting read-only monitoring behavior.

VirusTotal

66/66 vendors flagged this skill as clean.