ClawHub
Back to skill

Security audit

ADHD Sisterhood 晚确诊女性ADHD助手

Security checks across malware telemetry and agentic risk

Overview

This is a static Chinese-language ADHD support skill with disclosed educational health boundaries and no hidden code, persistence, or unrelated authority.

Installers should treat this as educational support, not medical care. Users should consult qualified clinicians for diagnosis, HRT, SSRIs, ADHD medications, medication changes, or crisis situations, and publishers should document whether the skill is intended for Chinese-speaking users only.

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)

Natural-Language Policy Violations

Medium
Confidence
89% confidence
Finding
The skill is written entirely in Chinese and strongly frames the persona and response style around Chinese output without indicating that language should follow the user's preference. This can create accessibility and usability issues, and in a health-adjacent support context it may cause misunderstanding or exclusion if a user interacts in another language.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The document gives medical-management advice including HRT, ADHD medications, and SSRI use without a clear warning that these are individualized prescription treatments requiring clinician supervision. In a user-facing skill, this can encourage self-medication, inappropriate treatment expectations, or delayed professional care, especially because menopause and ADHD are both clinically complex and medication risks vary by patient.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.