Recurring Loop Runner

Security checks across malware telemetry and agentic risk

Overview

This is a small instruction-only skill for scheduling recurring tasks, with the recurring behavior clearly disclosed and aligned with its purpose.

Install this only if you want your agent to create recurring tasks. Before using it, confirm the exact cadence, what will run, when it expires, and how to cancel it, and avoid scheduling sensitive or high-impact commands unless your platform has clear permission and rate controls.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
81% confidence
Finding
The default prompt, "Schedule this prompt on a recurring interval and run it immediately once," is broadly scoped and does not impose any constraints on what may be scheduled, how often it may run, or what safety checks should occur before repeated execution. In a recurring-execution skill, this can amplify risky user prompts, create unintended repeated actions, or enable abusive polling/command loops if downstream systems accept the instruction without additional validation.

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal