Incident Response Runbook

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent incident-response runbook helper with a small local script that only generates Markdown templates.

Install if you want incident runbook templates and triage prompts. During real outages, review any suggested commands or communications before using them, and avoid feeding sensitive incident history unless you are comfortable with the agent processing it.

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
87% confidence
Finding
The skill includes a very broad invocation phrase for active incident handling ('During Incident' with generic natural-language fields like 'Incident: [description]. Severity: [1-4]. Current symptoms: ... Help me triage and respond.'). In an agent environment, such common phrasing can accidentally trigger the skill during ordinary operational conversation, causing unintended runbook behavior, diagnostic guidance, or workflow activation at sensitive moments.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal