ClawHub
Back to skill

Security audit

Schedule

Security checks for vulnerabilities and agentic risk

Overview

This scheduling skill is not clearly malicious, but it asks for command and file authority for deferred tasks without strong limits or user confirmation.

Review this before installing if you plan to schedule tasks that run commands, edit files, call APIs, or repeat automatically. Only use it with clearly specified, low-risk tasks, and require explicit confirmation and allowlisted commands before enabling recurring execution.

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
Confidence
88% confidence
Finding
The skill is described in very broad terms while the metadata grants powerful tools including read, write, and exec. In an agent environment, vague invocation boundaries can cause the skill to be selected for loosely related requests, increasing the chance that untrusted user input flows into command execution, file writes, or external actions without clear user intent.

Missing User Warnings

High
Confidence
97% confidence
Finding
The skill exposes exec, write, and API-capable behavior but does not clearly warn users that invoking it may run commands, modify files, or contact external services. In a scheduling skill, this is especially dangerous because deferred or recurring execution can amplify the impact of a mistaken or maliciously phrased task over time.

Static analysis

No suspicious patterns detected.