NDIS Incident Reporting Specialist

Security checks across malware telemetry and agentic risk

Overview

This is a self-contained NDIS incident-reporting guidance skill with no executable code, hidden data access, or automatic submission behavior.

Use this as drafting and triage support, not as final legal or compliance advice. Because NDIS reporting rules and Commission guidance can change, verify deadlines and categories with a compliance lead or the NDIS Commission before submitting, especially for ambiguous, severe, or legally contested incidents.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Intent-Code Divergence

Medium
Confidence
92% confidence
Finding
The guardrails create a real ambiguity: one instruction says not to confirm reportability from incomplete facts and to ask for missing details first, while another says to default to reporting when in doubt. In practice, this can cause inconsistent agent behavior, including premature escalation or contradictory advice in time-sensitive regulatory workflows.

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal