Security audit

Cron Setup Guide Free

Security checks for vulnerabilities and agentic risk

Overview

This scheduling guide is not malicious, but it needs review because it can create persistent agent tasks and defaults omitted delivery settings toward external notification.

Install only if you are comfortable with an agent creating persistent scheduled jobs. Before using it, explicitly set delivery to none unless you want off-platform notifications, verify the exact Telegram or Discord recipient, avoid putting sensitive summaries in scheduled messages, and periodically review/remove cron 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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Missing User Warnings

High

Category: Not specified by scanner
Confidence: 96% confidence
Finding: Defaulting an omitted delivery configuration to 'announce' is dangerous because it can cause external notifications and transmission of task content without an explicit user choice. In a scheduling skill, this raises the risk of accidental disclosure of reminders, summaries, or operational data to Telegram or Discord recipients, especially when users assume missing delivery settings mean local-only behavior.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The skill encourages Telegram and Discord delivery of task outputs and recipient identifiers without a clear warning that task content and destination metadata will be transmitted to third-party services. This can lead users or agents to send sensitive summaries, messages, or personal contact data off-platform without informed consent or data classification checks.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: Line L252 states that the skill supports "创建/查询/导出操作", which actively represents export as a supported capability. However, the rest of the document only describes cron add/list/run/runs/edit/remove flows and never defines any export command or output path, so the documentation contradicts the actual documented behavior of the skill file.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The license/copyright section says the skill is '完全中文化表达，适配中文用户工作流', which signals a forced language/locale orientation. The file does not offer users an opt-in language choice or explain that the skill is intentionally region-specific for compliance or other justified reasons.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Low

Category: Not specified by scanner
Confidence: 78% confidence
Finding: The skill extends beyond cron configuration into generic command execution and network diagnostics such as ping testing. In an agent context with allowed tool access including exec, broad troubleshooting guidance can normalize unnecessary shell or network actions and increase the chance of misuse, especially if an agent follows the skill literally in sensitive environments.
Content: No source excerpt is available for this finding.