ClawHub
Back to skill

Security audit

Agent Heartbeat

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small markdown guide for configuring agent heartbeat tasks; its recurring automation purpose is disclosed, but users should scope any backups, syncs, or notifications carefully.

Install this only if you want help configuring recurring agent heartbeat tasks. Before using its examples, decide exactly which files may be backed up, what remote systems may be synced, who receives notifications, and how often the heartbeat may run.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

External Model or Provider Selection

Medium
Category
Excessive Agency
Content
---
name: agent-heartbeat
model: standard
description: Agent 心跳配置技能 — 配置 OpenClaw Agent 的定期心跳机制，保持在线状态，自动检查任务和更新。适用于需要长期运行的 Agent 任务。
---
Confidence
90% confidence
Finding
Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger list includes broad terms like '定期任务', '在线状态', 'cron', and 'schedule', which can match many ordinary user requests and cause this skill to activate outside narrowly intended heartbeat configuration scenarios. Because the skill deals with automated recurring actions, over-broad activation increases the chance of unsolicited guidance for persistent background behavior.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill recommends automated recurring actions such as checking tasks, sending status updates, backing up data, and syncing remote state, but it does not present user-facing warnings, approval boundaries, or safety constraints. In an agent context, recurring automation can create persistence, unintended network activity, privacy issues, or resource consumption if adopted without explicit consent and scope limits.

Static analysis

No suspicious patterns detected.