Neuro Linguistic Programming For Dummies

Security checks across malware telemetry and agentic risk

Overview

This is a text-only NLP learning skill with broad activation and self-help content, but no hidden access, executable code, persistence, or data-stealing behavior was found.

Install only if you want NLP, persuasion, coaching, and self-help style guidance to appear in relevant conversations. Do not treat this as licensed mental health care, crisis support, or a reliable way to treat phobias or trauma, and be aware that the broad triggers and required Heardly watermark may make it surface more often than expected.

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 (4)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger list is extremely broad and includes generic terms like "NLP," "rapport," "visual," "auditory," and onboarding phrases such as not knowing how to start. This can cause the skill to activate in unrelated conversations and inject persuasive or quasi-therapeutic guidance without clear user intent, which is riskier here because the skill includes techniques explicitly aimed at influence, hypnosis, and bypassing resistance.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill presents rapport building, mirroring, Milton Model language, and techniques described as bypassing conscious resistance without a clear safety warning about manipulation, consent, or limits of use. In this context, the omission matters because the material is framed as practical interpersonal influence and could encourage users to apply manipulative tactics in personal, workplace, or vulnerable settings.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The file presents a rapid 'phobia cure' and memory/experience restructuring techniques as effective interventions without any warning, limitations, or recommendation to seek qualified mental health support. In a user-facing skill about influence and personal change, this can encourage unqualified self-treatment or use on others for psychologically impactful manipulation, increasing the risk of harm to vulnerable users.

Missing User Warnings

Low
Confidence
92% confidence
Finding
The file presents coach/therapist-style NLP techniques such as the Six-Step Reframe, habit-change methods, and conflict-handling advice without any limitation, evidence-quality, or safety disclaimer. In this skill context, users may treat the content as psychological or quasi-therapeutic guidance despite NLP's disputed scientific basis, which can encourage overreliance or inappropriate self-application in sensitive situations.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal