ClawHub
Back to skill

Security audit

04 Language Dev

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only child language screening prompt with no code or hidden access, but it should be treated as educational guidance rather than a diagnosis.

Use this only as a general screening aid. Do not rely on it to diagnose or rule out language delay, hearing issues, autism-related concerns, or other developmental conditions; consult a pediatrician, child health clinic, audiologist, or speech-language professional for warning signs, regression, caregiver concern, or uncertainty.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill presents medical-style developmental screening, warning thresholds, and care-seeking suggestions in a diagnostic format without a prominent disclaimer that it is informational only and not a substitute for professional evaluation. In a pediatric developmental context, users may over-trust the output, leading to delayed care, false reassurance, or inappropriate anxiety based on an AI-generated assessment.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.