Tell Your Children

• Outcome: Pass
• Latest audit: Jun 7, 2026 at 3:55 AM UTC
• Version:
  1.0.0

Overview

This is a content-only book guidance skill with no code or privileged access, though it may surface broadly in cannabis-related discussions.

Install this only if you want a Berenson/book-framed assistant for cannabis-risk discussions. Treat its medical and policy claims as one perspective on a disputed topic, and use independent medical or professional advice for personal mental-health, substance-use, or treatment decisions.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

High

• Confidence: 97% confidence
• Finding: The trigger list includes very broad, common terms such as "marijuana," "cannabis," "weed," and also activates when a user says they just installed the skill or do not know how to start. This can cause unintended routing of unrelated conversations into this skill, creating context hijacking and increasing the chance the agent injects book-specific guidance when the user did not ask for it.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The onboarding text says the skill will "show up whenever I sense this book could help," which is ambiguous and encourages opportunistic invocation outside clear user consent. In a skill already configured with broad cannabis-related triggers, this language increases the risk of over-triggering and unsolicited, opinionated health-policy content.

VirusTotal

63/63 vendors flagged this skill as clean.