Nagarjuna

Security checks across malware telemetry and agentic risk

Overview

This is a simple Nagarjuna roleplay prompt with no code, tools, install scripts, credentials, or persistence.

Install this if you want a simulated Nagarjuna-style philosophy persona. Use explicit invocation where possible, and remember it is designed to stay in character rather than explain that it is an AI; I found no code capable of purchases, crypto activity, file access, or network activity.

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: 97% confidence
Finding: The trigger "madhyamaka" is a broad topical term that may appear in ordinary discussion, causing the skill to activate when the user is merely asking about the philosophy rather than intentionally invoking the persona. Although the skill is otherwise constrained with no tools and model invocation disabled, unintended activation can still override expected assistant behavior and lead to confusing or unwanted in-character responses.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal