Security audit

Cron Mate Free

Security checks across malware telemetry and agentic risk

Overview

This is a simple cron-expression helper with some confusing documentation, but no hidden persistence, credential use, destructive behavior, or exfiltration was found.

Before installing, treat it as a cron helper, not a general translation tool. Avoid relying on its privacy wording for sensitive schedules until the publisher clarifies whether only local Python examples are used or whether the agent's LLM may process inputs.

SkillSpector

By NVIDIA

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (2)

Intent-Code Divergence

Medium

Confidence: 95% confidence
Finding: The documentation makes conflicting trust claims: it says parsing is fully local and does not involve cloud calls, while also declaring an LLM API requirement and explicit model routing through GPT-4o-mini. This can mislead users about data flow, privacy, and compliance boundaries, causing them to submit sensitive scheduling or operational information under false assumptions.

Vague Triggers

Medium

Confidence: 84% confidence
Finding: The skill advertises an overly broad activation scope, including unrelated translation/localization scenarios that exceed the stated cron-assistance purpose. Overbroad routing can cause the agent to invoke this skill in unintended contexts, increasing prompt-surface area, user confusion, and the chance that unrelated user content is processed under misleading assumptions.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.