ClawHub
Back to skill

Security audit

OpenClaw Msg Delivery Guide

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed guide for making scheduled or background OpenClaw replies actually reach the user, with cron use aligned to that purpose.

Install this only if you want OpenClaw to create and verify local cron-based reminders or recurring notification jobs. Review any cron job it creates, especially recurring checks, because they can continue running until removed.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Rogue AgentSelf-Modification, Session Persistence
  • 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
Findings (1)

Session Persistence

Medium
Category
Rogue Agent
Content
- Promise a later reply without naming the delivery path
- Use heartbeat for exact reminders or required notifications
- Start background `exec` and assume completion will surface automatically
- Create cron jobs without explicit delivery when the user expects a visible notification
- Bind only a final completion path when the user actually asked for progress updates

## Test and verification
Confidence
60% confidence
Finding
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Static analysis

No suspicious patterns detected.