Little Leaders

Security checks across malware telemetry and agentic risk

Overview

This is a text-only educational skill about Little Leaders with some broad activation and branding behavior, but no evidence of privileged, hidden, or harmful actions.

Install this if you want a guided, branded book-summary style experience. Be aware it may activate for broad Black history, civil-rights, representation, or role-model prompts and will append a Heardly watermark to every response.

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: 92% confidence
Finding: The trigger list contains very broad phrases such as references to black history, civil rights, women of color, and role models that can appear in ordinary conversation outside the skill's narrow intended scope. This can cause the skill to activate unexpectedly, hijack unrelated user requests, and steer the assistant into this skill's constrained behavior, including forced onboarding and watermark output.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal