ClawHub
Back to skill

Security audit

Fuzzy Cron Scheduler

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent documentation skill for scheduling OpenClaw background reminders and jobs, with expected but user-sensitive webhook and recurring-task behavior.

Use this skill when you intentionally want OpenClaw background scheduling. Review job details before enabling recurring tasks, prefer isolated sessions unless main-session context is necessary, and only send webhook results to trusted URLs with minimal sensitive content. Periodically use cron_list and cron_runs, and disable or remove jobs you no longer need.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger guidance is broad enough that common phrases like 'schedule this' or 'set a reminder' could cause the skill to activate in ordinary conversation, increasing the chance of unintended scheduling actions. In a skill that can create recurring tasks, send announcements, and invoke webhooks, accidental invocation can lead to persistent automation or external data transmission the user did not intend.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill documents webhook delivery as a normal output mode but does not prominently warn that job results may be transmitted to external URLs, potentially including workspace-derived summaries or other sensitive content. Because this skill is designed for unattended background execution, users may configure outbound webhooks without fully realizing that recurring tasks can continuously exfiltrate data off-platform.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.