scheduler notification runbook

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only scheduling runbook with disclosed reminder, agent-run, and webhook patterns that fit its stated purpose.

Before installing, treat this as guidance for scheduler workflows, not executable code. When using webhook delivery or scheduled agent runs, confirm the destination and payload with the user, avoid secrets or unnecessary personal data, and periodically review recurring or named-session jobs.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The runbook explicitly recommends `delivery.mode = "webhook"` for scheduled runs that call an external HTTP endpoint, but it does not instruct the agent to warn the user or confirm consent before transmitting data outside the chat system. In a scheduling skill, this omission is meaningful because future agent runs may send summaries, context, or operational data to third-party services, creating a risk of unintended data exfiltration or privacy violations.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal