Runbook Automator

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward runbook automation helper, but generated playbooks can run operational commands and send optional incident notifications externally.

Install only if you are comfortable reviewing generated shell scripts before running them. Keep dry-run enabled during validation, use least-privilege operational credentials, confirm Slack or PagerDuty destinations, and avoid sending sensitive incident details to unapproved external channels.

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: 94% confidence
Finding: The skill generates automation that can send notifications to external services using environment-provided webhook/API secrets, but it does not instruct the user to review what data is sent or to limit sensitive content. In a runbook-automation context, generated messages may include incident details, hostnames, service names, or failure text derived from internal operations, creating a realistic risk of unintended data egress.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal