Security audit

定时守护

Security checks across malware telemetry and agentic risk

Overview

This cron reliability skill is mostly documentation, but it asks for command and file authority while giving inconsistent guidance about API keys, networking, and execution scope.

Review this skill before installing. It appears to be a Markdown-only cron hardening guide with no bundled executable files, but it requests read/write/exec authority and contains generic API, credential, network, and command-execution instructions that are broader than its stated cron reliability purpose. Use it only with explicit approval for state-changing commands, avoid providing API keys unless a specific guarded script truly needs them, and keep generated cron jobs scoped to known files and commands.

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 (6)

Intent-Code Divergence

Medium

Confidence: 92% confidence
Finding: The document makes contradictory security claims about API key requirements: one section says the skill does not require API keys, while later sections instruct users to configure them and even discuss API authentication failures. This inconsistency can cause users or agents to mis-handle secrets, either exposing unnecessary credentials or failing to apply proper secret-management controls when the skill actually invokes external services.

Intent-Code Divergence

Medium

Confidence: 90% confidence
Finding: The skill is described in one place as Markdown-only guidance, but elsewhere it is presented as EXEC-capable and able to execute commands. That mismatch is dangerous because users may trust it as passive documentation while the agent interprets it as permission to run commands that modify the system or process sensitive data.

Intent-Code Divergence

Medium

Confidence: 89% confidence
Finding: The document says scripts should not include network access, yet other sections normalize HTTPS communication, API integration, and network-related troubleshooting. This contradiction can mislead operators into allowing outbound network behavior they believed was disallowed, increasing the risk of data exfiltration, unintended external calls, or policy violations in unattended cron contexts.

Description-Behavior Mismatch

High

Confidence: 95% confidence
Finding: The manifest presents a narrow cron/job reliability hardening skill, but later sections expand it into broad file processing, API integration, information retrieval, and general automation. This scope drift is risky because it can cause an agent or user to grant broader trust and permissions than the original skill purpose justifies, enabling unintended command, file, or network operations under a benign-looking label.

Context-Inappropriate Capability

Medium

Confidence: 93% confidence
Finding: The skill introduces external API integration and credential setup despite being framed as a cron reliability guard. Adding unrelated external-service and credential-handling behavior expands attack surface unnecessarily and may cause users to provide secrets to a skill that should not need them for its core function.

Missing User Warnings

Medium

Confidence: 88% confidence
Finding: The skill advertises file writing, command execution, and external API use without a clear user-facing warning about their impact on system state or user data. In an automation context, especially for scheduled jobs, this can lead users to approve or deploy the skill without understanding that it may modify files, execute commands, or transmit data externally.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.