Risk Management Playbook

Security checks across malware telemetry and agentic risk

Overview

This is a Markdown-only risk management advice playbook with a broad trigger, but no hidden execution, credential use, or privileged behavior was found.

Before installing, verify the GitHub repository and publisher because the README uses a global --yes install command. Treat the output as a general playbook, not legal, regulatory, insurance, sanctions, AML, security-incident, or crisis-specific professional advice; validate recommendations against your jurisdiction, industry, and qualified experts before acting.

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

High
Confidence
98% confidence
Finding
The manifest description says to trigger on "ANY risk management" or "enterprise risk topic" and adds "If in doubt, use this skill." Those phrases are unusually broad for a skill trigger and do not define meaningful boundaries or exclusions, creating a high likelihood of accidental invocation during ordinary business conversations.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal