ClawHub
Back to skill

Security audit

Agent Lifecycle Manager

Security checks across malware telemetry and agentic risk

Overview

This skill performs powerful but clearly described OpenClaw agent management tasks, with the main risk being local archives that may contain sensitive agent data.

Install this only if you want the agent to administer local OpenClaw agents. Before running helpers, verify the agent ID, Telegram token, pairing code, archive path, any --inherit-auth use, and any --yes deletion bypass. Keep generated archives and state files private because they may include credentials, configuration, chat history, or workspace data.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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)

Missing User Warnings

Medium
Confidence
81% confidence
Finding
The script archives agent state, workspace contents, and multiple OpenClaw status outputs to disk without any confirmation, minimization, or disclosure to the operator. In this lifecycle-management context, those locations can contain credentials, configuration secrets, chat logs, or other sensitive operational data, so creating persistent copies increases exposure if the archive path is later accessed by other users, backups, or unrelated tooling.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.