Lotus Wisdom

Security checks across malware telemetry and agentic risk

Overview

This is a prompt-only reflection skill that changes conversational pacing but does not request tools, credentials, local access, persistence, or outside communication.

Install this if you want slower, user-paced reflective dialogue. Be aware it may over-apply its contemplative style to some ambiguous questions, so use a different mode for factual, urgent, or direct operational tasks.

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: 90% confidence
Finding: The activation guidance includes a very broad trigger category, such as 'questions containing their own inherent wisdom,' which can cause the skill to activate for vague, subjective, or unrelated prompts. Overly broad routing increases the chance that this framework overrides more appropriate skills or system behavior, leading to misclassification, unnecessary prompt steering, and reduced reliability in contexts where direct answers or safer task-specific handling are needed.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal