ClawHub
Back to skill

Security audit

OpenClaw Waste Audit

Security checks across malware telemetry and agentic risk

Overview

This skill is a read-only OpenClaw token-waste audit guide with clear limits and no executable payload.

Install only if you want an agent to inspect OpenClaw cron job metadata and run summaries for token waste. Treat job names, summaries, logs, paths, and delivery details as potentially private, and follow the skill's own guidance to redact secrets before sharing any examples externally.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Low
Confidence
82% confidence
Finding
The reference file includes the job name "Agent控制权_每日特别提醒," which mixes Chinese text into the documented workflow context. Under the policy, language-specific content can be a violation when a specific language is imposed without user opt-in or documented regional justification, and this file does not provide that context.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.