Boot Resume

Security checks across malware telemetry and agentic risk

Overview

This recovery skill is disclosed and purpose-aligned, but it installs persistent automation that can automatically resume agent work without a fresh user approval.

Review before installing. Use this only if you explicitly want OpenClaw agents to resume interrupted work automatically after gateway restarts or system wake. Inspect or supply the missing systemd template files first, and avoid enabling it for agents that can perform high-risk actions unless you add confirmation, narrower agent/session scope, or a dry-run mode.

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
85% confidence
Finding
The README explicitly describes automatically injecting resume events into interrupted sessions, which modifies session state and can cause actions to continue without a fresh user confirmation. In a recovery skill, this behavior is core functionality, but documenting it without a clear safety warning or operator confirmation model increases the risk of unintended tool execution, duplicate actions, or resuming sensitive workflows after a crash.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal