Everybody A Book About Freedom

Security checks across malware telemetry and agentic risk

Overview

This is a non-executable book companion skill with some overbroad activation and underqualified wellness language, but no hidden access or unsafe runtime behavior.

Install this if you want a themed guide to the book, but expect it may activate on broad freedom/body-politics prompts. Treat any therapy or trauma-healing language as discussion of the book's themes, not medical or mental-health advice.

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: 91% confidence
Finding: The trigger list includes highly generic terms such as "Everybody," "Freedom," and phrases indicating a user just installed the skill or does not know how to start. These broad conditions can cause unintended invocation in unrelated conversations, leading to context hijacking, degraded routing, and increased chance the assistant applies this skill when the user did not request book-specific guidance.

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The line presents trauma-healing advice as broadly applicable fact ('Trauma is stored as physical tension' and that therapy, movement, touch, and breath can release it) without qualification, safety limits, or direction to licensed care. In a general-purpose conversational skill, users may interpret this as therapeutic or medical guidance, which can mislead vulnerable users, especially those with trauma histories, dissociation, or touch-related triggers.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal