ClawHub
Back to skill

Security audit

Smart Cron

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed scheduler for OpenClaw tasks, with expected persistence and alerts that users should configure carefully.

Before installing, confirm you are comfortable with persistent scheduled OpenClaw tasks, local logs of job activity, and any configured WhatsApp or Telegram failure alerts that may include task names and error details. Use pause, remove, and log-retention settings for jobs that handle sensitive work.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill advertises WhatsApp/Telegram failure alerts and shows example alerts containing task names, timing, errors, and log references, but it does not clearly warn that task-related metadata may be transmitted to third-party messaging services. If tasks contain sensitive business, personal, or system information, failure notifications could leak that information outside the local environment.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

This is a manifest file, so vague-trigger checks apply. The description emphasizes "plain English" scheduling with examples like "Every weekday at 9am" and "every 30 minutes," but it does not define specific trigger phrases, invocation boundaries, or exclusion conditions, which could cause unintended activation from ordinary conversation about schedules.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill does disclose the storage path and says data is stored locally, but it does not present this as a user-facing warning or explain the privacy/security implications of persistent retention of job configurations and execution logs. Because scheduled tasks may contain sensitive prompts, operational details, or output history, users may unknowingly leave recoverable data on disk for extended periods.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.