incident-manager

Security checks across malware telemetry and agentic risk

Overview

This is a plain incident-management guidance skill with templates and no executable code, credentials, persistence, or hidden data handling.

Reasonable to install if you want help structuring incident response, post-mortems, and runbooks. Invoke it explicitly for real incidents, verify severity and stakeholder communications yourself, and avoid pasting confidential customer, outage, or business-impact details unless you are comfortable sharing them with the agent.

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
89% confidence
Finding
The manifest description includes broad trigger phrases such as incident response, analysis, prevention, and classification, which can match many generic operational or troubleshooting requests outside a narrowly scoped incident-declaration skill. Over-broad invocation increases the chance the agent routes unrelated sensitive workflows here, causing inappropriate actions, misleading guidance, or unnecessary exposure of incident-handling procedures in contexts where they do not belong.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal