McKinsey Presentation Generator

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only presentation generator whose research, slide creation, and deployment steps are disclosed and aligned with its purpose.

Safe to install for normal presentation work. Avoid using confidential company plans, client names, or private data unless you are comfortable with external search queries and with the final deck being deployed or shared after review.

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 (2)

Vague Triggers

Medium

Confidence: 84% confidence
Finding: The skill lists triggers but does not define clear activation boundaries, fallback behavior, or exclusions, creating ambiguous invocation semantics. In agent systems, ambiguous routing can cause inappropriate tool use, accidental web research, or generation of high-effort outputs in response to generic user phrasing.

Vague Triggers

Medium

Confidence: 84% confidence
Finding: The skill lists triggers but does not define clear activation boundaries, fallback behavior, or exclusions, creating ambiguous invocation semantics. In agent systems, ambiguous routing can cause inappropriate tool use, accidental web research, or generation of high-effort outputs in response to generic user phrasing.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal